dreamplayer-zhang / Awesome-CVPR2023-Low-Level-Vision

A Collection of Papers and Codes in CVPR2023/2022 about low level vision

Awesome-CVPR2023-Low-Level-Vision

A Collection of Papers and Codes in CVPR2023 related to Low-Level Vision

[Completed] If you find some missing papers or typos, feel free to pull issues or requests.

Related collections for low-level vision

• Awesome-ICCV2023/2021-Low-Level-Vision
• Awesome-CVPR2022-Low-Level-Vision
• Awesome-NeurIPS2022/2021-Low-Level-Vision
• Awesome-ECCV2022-Low-Level-Vision
• Awesome-AAAI2022-Low-Level-Vision
• Awesome-CVPR2021/2020-Low-Level-Vision
• Awesome-ECCV2020-Low-Level-Vision

Overview

• Image Restoration

  • Video Restoration

• Super Resolution

  • Image Super Resolution
  • Video Super Resolution

• Image Rescaling

• Denoising

  • Image Denoising

• Deblurring

  • Image Deblurring
  • Video Deblurring

• Deraining

• Dehazing

• HDR Imaging / Multi-Exposure Image Fusion

• Frame Interpolation

• Image Enhancement

  • Low-Light Image Enhancement

• Image Harmonization

• Image Completion/Inpainting

• Image Matting

• Image Compression

• Image Quality Assessment

• Style Transfer

• Image Editing

• Image Generation/Synthesis/ Image-to-Image Translation

  • Video Generation

• Others

Image Restoration

Efficient and Explicit Modelling of Image Hierarchies for Image Restoration

• Paper: https://arxiv.org/abs/2303.00748
• Code: https://github.com/ofsoundof/GRL-Image-Restoration
• Tags: Transformer

Comprehensive and Delicate: An Efficient Transformer for Image Restoration

• Paper: CVPR Open Access Version
• Tags: Transformer

Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective

• Paper: https://arxiv.org/abs/2303.06859
• Code: https://github.com/lixinustc/Casual-IRDIL

Generative Diffusion Prior for Unified Image Restoration and Enhancement

• Paper: https://arxiv.org/abs/2304.01247
• Code: https://github.com/Fayeben/GenerativeDiffusionPrior

DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration

• Paper: https://arxiv.org/abs/2303.06885
• Tags: Diffusion, Blind Face

Bitstream-Corrupted JPEG Images are Restorable: Two-stage Compensation and Alignment Framework for Image Restoration

• Paper: https://arxiv.org/abs/2304.06976
• Code: https://github.com/wenyang001/Two-ACIR

All-in-One Image Restoration for Unknown Degradations Using Adaptive Discriminative Filters for Specific Degradations

• Paper: CVPR Open Access Version

Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions

• Paper: CVPR Open Access Version
• Code: https://github.com/zhuyr97/WGWS-Net
• Tags: Multiple Adverse Weather

AccelIR: Task-Aware Image Compression for Accelerating Neural Restoration

• Paper: CVPR Open Access Version
• Tags: Image Compression for Accelerating

Robust Unsupervised StyleGAN Image Restoration

• Paper: https://arxiv.org/abs/2302.06733
• Tags: StyleGAN

Ingredient-Oriented Multi-Degradation Learning for Image Restoration

• Paper: CVPR Open Access Version

Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank

• Paper: https://arxiv.org/abs/2303.09101
• Code: https://github.com/Huang-ShiRui/Semi-UIR
• Tags: Underwater Image Restoration

Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior

• Paper: https://arxiv.org/abs/2303.15046
• Code: https://github.com/ykdai/BracketFlare
• Tags: Reflective Flare Removal

Robust Single Image Reflection Removal Against Adversarial Attacks

• Paper: CVPR Open Access Version
• Tags: Reflection Removal

ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal

• Paper: https://arxiv.org/abs/2212.04711
• Code: https://github.com/GuoLanqing/ShadowDiffusion
• Tags: Diffusion, Shadow Removal

Document Image Shadow Removal Guided by Color-Aware Background

• Paper: CVPR Open Access Version
• Code: https://github.com/hyyh1314/BGShadowNet
• Tags: Shadow Removal

Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display Camera

• Paper: https://arxiv.org/abs/2304.06019
• Code: https://github.com/jnjaby/AlignFormer

GamutMLP: A Lightweight MLP for Color Loss Recovery

• Paper: https://arxiv.org/abs/2304.11743
• Code: https://github.com/hminle/gamut-mlp
• Tags: restore wide-gamut color values

ABCD: Arbitrary Bitwise Coefficient for De-Quantization

• Paper: CVPR Open Access Version
• Code: https://github.com/WooKyoungHan/ABCD
• Tags: De-quantization/Bit depth expansion

Visual Recognition-Driven Image Restoration for Multiple Degradation With Intrinsic Semantics Recovery

• Paper: CVPR Open Access Version
• Tags: Restoration for High-Level Tasks

Parallel Diffusion Models of Operator and Image for Blind Inverse Problems

• Paper: https://arxiv.org/abs/2211.10656
• Code: https://github.com/BlindDPS/blind-dps
• Tags: blind deblurring, and imaging through turbulence

Image Reconstruction

Raw Image Reconstruction with Learned Compact Metadata

• Paper: https://arxiv.org/abs/2302.12995
• Code: https://github.com/wyf0912/R2LCM

High-resolution image reconstruction with latent diffusion models from human brain activity

• Paper: https://www.biorxiv.org/content/10.1101/2022.11.18.517004v2
• Code: https://github.com/yu-takagi/StableDiffusionReconstruction

Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder

• Paper: https://arxiv.org/abs/2305.02541

Optimization-Inspired Cross-Attention Transformer for Compressive Sensing

• Paper: https://arxiv.org/abs/2304.13986
• Code: https://github.com/songjiechong/OCTUF
• Tags: Compressive Sensing

Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding

• Paper: https://arxiv.org/abs/2211.06956
• Code: https://github.com/zjc062/mind-vis

Burst Restoration

Burstormer: Burst Image Restoration and Enhancement Transformer

• Paper: https://arxiv.org/abs/2304.01194
• Code: https://github.com/akshaydudhane16/Burstormer

Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement

• Paper: https://arxiv.org/abs/2304.06703

Video Restoration

A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift

• Paper: https://arxiv.org/abs/2206.10810
• Code: https://github.com/dasongli1/Shift-Net

HNeRV: A Hybrid Neural Representation for Videos

• Paper: https://arxiv.org/abs/2304.02633
• Code: https://github.com/haochen-rye/HNeRV

Blind Video Deflickering by Neural Filtering with a Flawed Atlas

• Paper: https://arxiv.org/abs/2303.08120
• Code: https://github.com/ChenyangLEI/All-In-One-Deflicker
• Tags: Deflickering

[Back-to-Overview]

Super Resolution

Image Super Resolution

Activating More Pixels in Image Super-Resolution Transformer

• Paper: https://arxiv.org/abs/2205.04437
• Code: https://github.com/XPixelGroup/HAT
• Tags: Transformer

N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution

• Paper: https://arxiv.org/abs/2211.11436
• Code: https://github.com/rami0205/NGramSwin

Omni Aggregation Networks for Lightweight Image Super-Resolution

• Paper: https://arxiv.org/abs/2304.10244
• Code: https://github.com/Francis0625/Omni-SR

OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution

• Paper: https://arxiv.org/abs/2303.01091
• Tags: Arbitrary-Scale SR

Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution

• Paper: https://arxiv.org/abs/2303.05156
• Tags: Normalizing Flow, Arbitrary-Scale SR

Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution

• Paper: https://arxiv.org/abs/2303.16513
• Code: https://github.com/jaroslaw1007/CLIT
• Tags: Arbitrary-Scale SR, Transformer

Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit

• Paper: CVPR Open Access Version
• Code: https://github.com/neuralchen/EQSR
• Tags: Arbitrary-Scale SR

CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution

• Paper: https://arxiv.org/abs/2212.04362
• Tags: Arbitrary-Scale SR

Super-Resolution Neural Operator

• Paper: https://arxiv.org/abs/2303.02584
• Code: https://github.com/2y7c3/Super-Resolution-Neural-Operator

Human Guided Ground-truth Generation for Realistic Image Super-resolution

• Paper: https://arxiv.org/abs/2303.13069
• Code: https://github.com/ChrisDud0257/PosNegGT

Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution

• Paper: https://arxiv.org/abs/2304.03542
• Tags: Blind

Implicit Diffusion Models for Continuous Super-Resolution

• Paper: https://arxiv.org/abs/2303.16491
• Code: https://github.com/Ree1s/IDM
• Tags: Diffusion

CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Input

• Paper: https://arxiv.org/abs/2304.06454

Spectral Bayesian Uncertainty for Image Super-Resolution

• Paper: CVPR Open Access Version

Cross-Guided Optimization of Radiance Fields With Multi-View Image Super-Resolution for High-Resolution Novel View Synthesis

• Paper: CVPR Open Access Version

Image Super-Resolution Using T-Tetromino Pixels

• Paper: CVPR Open Access Version

Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis

• Paper: CVPR Open Access Version

Equivalent Transformation and Dual Stream Network Construction for Mobile Image Super-Resolution

• Paper: CVPR Open Access Version
• Code: https://github.com/ECNUSR/ETDS

Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimation

• Paper: https://arxiv.org/abs/2211.13676
• Code: https://github.com/seungho-snu/SROOE

OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer

• Paper: https://arxiv.org/abs/2302.03453
• Code: https://github.com/Fanghua-Yu/OSRT
• Tags: Transformer, Omnidirectional SR

B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution

• Paper: CVPR Open Access Version
• Code: https://github.com/ByeongHyunPak/btc

Spatial-Frequency Mutual Learning for Face Super-Resolution

• Paper: CVPR Open Access Version
• Code: https://github.com/wcy-cs/SFMNet
• Tags: Face SR

Learning Generative Structure Prior for Blind Text Image Super-resolution

• Paper: https://arxiv.org/abs/2303.14726
• Code: https://github.com/csxmli2016/MARCONet
• Tags: Text SR

Guided Depth Super-Resolution by Deep Anisotropic Diffusion

• Paper: https://arxiv.org/abs/2211.11592
• Code: https://github.com/prs-eth/Diffusion-Super-Resolution
• Tags: Guided Depth SR

Toward Stable, Interpretable, and Lightweight Hyperspectral Super-Resolution

• Paper: CVPR Open Access Version
• Code: https://github.com/WenjinGuo/DAEM
• Tags: Hyperspectral SR

Zero-Shot Dual-Lens Super-Resolution

• Paper: https://openaccess.thecvf.com/content/CVPR2023/html/Xu_Zero-Shot_Dual-Lens_Super-Resolution_CVPR_2023_paper.html
• Code: https://github.com/XrKang/ZeDuSR

Probability-based Global Cross-modal Upsampling for Pansharpening

• Paper: https://arxiv.org/abs/2303.13659
• Code: https://github.com/Zeyu-Zhu/PGCU
• Tags: Pansharpening(for remote sensing image)

CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending

• Paper: CVPR Open Access Version
• Code: https://github.com/zeyuxiao1997/CutMIB
• Tags: Light Field SR

Quantum Annealing for Single Image Super-Resolution

• Paper: https://arxiv.org/abs/2304.08924
• Tags: [Workshop]

Bicubic++: Slim, Slimmer, Slimmest -- Designing an Industry-Grade Super-Resolution Network

• Paper: https://arxiv.org/abs/2305.02126
• Code: https://github.com/aselsan-research-imaging-team/bicubic-plusplus
• Tags: [Workshop]

Hybrid Transformer and CNN Attention Network for Stereo Image Super-resolution

• Paper: https://arxiv.org/abs/2305.05177
• Tags: [Workshop]

Video Super Resolution

Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting

• Paper: https://arxiv.org/abs/2303.08331
• Code: https://github.com/coulsonlee/STDO-CVPR2023

Structured Sparsity Learning for Efficient Video Super-Resolution

• Paper: https://github.com/Zj-BinXia/SSL
• Code: https://arxiv.org/abs/2206.07687

Compression-Aware Video Super-Resolution

• Paper: CVPR Open Access Version

Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution

• Paper: https://arxiv.org/abs/2303.13767
• Project: https://vlis2022.github.io/cvpr23/egvsr
• Tags: Event

Consistent Direct Time-of-Flight Video Depth Super-Resolution

• Paper: https://arxiv.org/abs/2211.08658
• Code: https://github.com/facebookresearch/DVSR/
• Tags: Depth SR

[Back-to-Overview]

Image Rescaling

HyperThumbnail: Real-time 6K Image Rescaling with Rate-distortion Optimization

• Paper: https://arxiv.org/abs/2304.01064
• Code: https://github.com/AbnerVictor/HyperThumbnail

DINN360: Deformable Invertible Neural Network for Latitude-Aware 360deg Image Rescaling

• Paper: CVPR Open Access Version
• Code: https://github.com/gyc9709/DINN360

[Back-to-Overview]

Denoising

Image Denoising

Masked Image Training for Generalizable Deep Image Denoising

• Paper: https://arxiv.org/abs/2303.13132
• Code: https://github.com/haoyuc/MaskedDenoising

Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising

• Paper: https://arxiv.org/abs/2303.14934
• Cdoe: https://github.com/nagejacob/SpatiallyAdaptiveSSID
• Tags: Self-Supervised

LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising

• Paper: https://arxiv.org/abs/2304.00534
• Code: https://github.com/Wang-XIaoDingdd/LGBPN
• Tags: Self-Supervised

Real-time Controllable Denoising for Image and Video

• Paper: https://arxiv.org/pdf/2303.16425.pdf

Zero-Shot Noise2Noise: Efficient Image Denoising without any Data

• Paper: https://arxiv.org/abs/2303.11253
• Code: https://colab.research.google.com/drive/1i82nyizTdszyHkaHBuKPbWnTzao8HF9b
• Tags: Zero-Shot

Patch-Craft Self-Supervised Training for Correlated Image Denoising

• Paper: https://arxiv.org/abs/2211.09919
• Tags: Self-Supervised

sRGB Real Noise Synthesizing with Neighboring Correlation-Aware Noise Model

• Paper: CVPR Open Access Version
• Code: https://github.com/xuan611/sRGB-Real-Noise-Synthesizing
• Tags: Real Noise Synthesizing

Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising

• Paper: https://arxiv.org/abs/2304.00844
• Code: https://github.com/MyuLi/SERT
• Tags: Hyperspectral

Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representations

• Paper: https://arxiv.org/abs/2303.18139
• Tags: 3D

Structure Aggregation for Cross-Spectral Stereo Image Guided Denoising

• Paper: CVPR Open Access Version
• Code: https://github.com/lustrouselixir/SANet
• Tags: Stereo Image

Polarized Color Image Denoising

• Paper: CVPR Open Access Version
• Code: https://github.com/bandasyou/pcdenoise
• Tags: Polarized Color Image

[Back-to-Overview]

Deblurring

Image Deblurring

Structured Kernel Estimation for Photon-Limited Deconvolution

• Paper: https://arxiv.org/abs/2303.03472
• Code: https://github.com/sanghviyashiitb/structured-kernel-cvpr23

Blur Interpolation Transformer for Real-World Motion from Blur

• Paper: https://arxiv.org/abs/2211.11423
• Code: https://github.com/zzh-tech/BiT

Neumann Network with Recursive Kernels for Single Image Defocus Deblurring

• Paper: CVPR Open Access Version
• Code: https://github.com/csZcWu/NRKNet

Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring

• Paper: https://arxiv.org/abs/2211.12250
• Code: https://github.com/kkkls/FFTformer

Hybrid Neural Rendering for Large-Scale Scenes with Motion Blur

• Paper: https://arxiv.org/abs/2304.12652
• Code: https://github.com/CVMI-Lab/HybridNeuralRendering

Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring

• Paper: CVPR Open Access Version
• Code: https://github.com/Fangzhenxuan/UFPDeblur
• Tag: Self-Supervised

Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior

• Paper: https://arxiv.org/abs/2210.05361
• Code: https://github.com/xl-tang01/UAUDeblur
• Tags: Unsupervised

K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring

• Paper: CVPR Open Access Version

Self-Supervised Blind Motion Deblurring With Deep Expectation Maximization

• Paper: CVPR Open Access Version
• Tags: Self-Supervised

HyperCUT: Video Sequence from a Single Blurry Image using Unsupervised Ordering

• Paper: https://arxiv.org/abs/2304.01686
• Code: https://github.com/VinAIResearch/HyperCUT

Video Deblurring

Deep Discriminative Spatial and Temporal Network for Efficient Video Deblurring

• Paper: CVPR Open Access Version
• Code: https://github.com/xuboming8/DSTNet

[Back-to-Overview]

Deraining

Learning A Sparse Transformer Network for Effective Image Deraining

• Paper: https://arxiv.org/abs/2303.11950
• Code: https://github.com/cschenxiang/DRSformer

SmartAssign: Learning a Smart Knowledge Assignment Strategy for Deraining and Desnowing

• Paper: CVPR Open Access Version
• Code: https://gitee.com/mindspore/models/tree/master/research/cv/SmartAssign

[Back-to-Overview]

Dehazing

RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors

• Paper: https://arxiv.org/abs/2304.03994
• Code: https://github.com/RQ-Wu/RIDCP

Curricular Contrastive Regularization for Physics-aware Single Image Dehazing

• Paper: https://arxiv.org/abs/2303.14218
• Code: https://github.com/YuZheng9/C2PNet

Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior

• Paper: https://arxiv.org/abs/2303.09757
• Code: https://github.com/jiaqixuac/MAP-Net

SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing

• Paper: https://arxiv.org/abs/2304.08444
• Code: https://github.com/gy65896/SCANet
• Tags: [Workshop]

Streamlined Global and Local Features Combinator (SGLC) for High Resolution Image Dehazing

• Paper: https://arxiv.org/abs/2304.13375
• Tags: [Workshop]

[Back-to-Overview]

HDR Imaging / Multi-Exposure Image Fusion

Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Models

• Paper: https://arxiv.org/abs/2303.13031
• Code: https://github.com/AndreGuo/HDRTVDM

SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders

• Paper: https://arxiv.org/abs/2304.06914

A Unified HDR Imaging Method with Pixel and Patch Level

• Paper: https://arxiv.org/abs/2304.06943

Inverting the Imaging Process by Learning an Implicit Camera Model

• Paper: https://arxiv.org/abs/2304.12748
• Code: https://github.com/xhuangcv/neucam
• Tags: generating all-in-focus photos & HDR imaging

Joint HDR Denoising and Fusion: A Real-World Mobile HDR Image Dataset

• Paper: CVPR Open Access Version
• Code: https://github.com/shuaizhengliu/Joint-HDRDN

HDR Imaging with Spatially Varying Signal-to-Noise Ratios

• Paper: https://arxiv.org/abs/2303.17253

1000 FPS HDR Video with a Spike-RGB Hybrid Camera

• Paper: CVPR Open Access Version

[Back-to-Overview]

Frame Interpolation

Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation

• Paper: https://arxiv.org/abs/2303.00440
• Code: https://github.com/MCG-NJU/EMA-VFI

A Unified Pyramid Recurrent Network for Video Frame Interpolation

• Paper: https://arxiv.org/abs/2211.03456
• Code: https://github.com/srcn-ivl/UPR-Net

BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation

• Paper: https://arxiv.org/abs/2304.02225
• Code: https://github.com/JunHeum/BiFormer

AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation

• Paper: https://arxiv.org/abs/2304.09790
• Code: https://github.com/MCG-NKU/AMT

Exploring Discontinuity for Video Frame Interpolation

• Paper: https://arxiv.org/abs/2202.07291
• Code: https://github.com/pandatimo/Exploring-Discontinuity-for-VFI

Frame Interpolation Transformer and Uncertainty Guidance

• Paper: CVPR Open Access Version

Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation

• Paper: https://arxiv.org/abs/2203.10291

Range-Nullspace Video Frame Interpolation With Focalized Motion Estimation

• Paper: CVPR Open Access Version

Event-based Video Frame Interpolation with Cross-Modal Asymmetric Bidirectional Motion Fields

• Paper: CVPR Open Access Version
• Code: https://github.com/intelpro/CBMNet
• Tags: Event-based

Event-based Blurry Frame Interpolation under Blind Exposure

• Paper: CVPR Open Access Version
• Code: https://github.com/WarranWeng/EBFI-BE
• Tags: Event-based

Event-Based Frame Interpolation with Ad-hoc Deblurring

• Paper: https://arxiv.org/abs/2301.05191
• Tags: Event-based

Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time

• Paper: https://arxiv.org/abs/2303.15043
• Code: https://github.com/shangwei5/VIDUE
• Tags: Frame Interpolation and Deblurring

[Back-to-Overview]

Image Enhancement

Realistic Saliency Guided Image Enhancement

• Paper: CVPR Open Access Version
• Code: https://github.com/compphoto/RealisticImageEnhancement

Low-Light Image Enhancement

Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement

• Paper: https://arxiv.org/abs/2304.07039
• Code: https://github.com/langmanbusi/Semantic-Aware-Low-Light-Image-Enhancement

Visibility Constrained Wide-band Illumination Spectrum Design for Seeing-in-the-Dark

• Paper: https://arxiv.org/abs/2303.11642
• Code: https://github.com/MyNiuuu/VCSD
• Tags: NIR2RGB

DNF: Decouple and Feedback Network for Seeing in the Dark

• Paper: CVPR Open Access Version
• Code: https://github.com/Srameo/DNF

You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement

• Paper: CVPR Open Access Version

Low-Light Image Enhancement via Structure Modeling and Guidance

• Paper: https://arxiv.org/abs/2305.05839

Learning a Simple Low-light Image Enhancer from Paired Low-light Instances

• Paper: CVPR Open Access Version
• Code: https://github.com/zhenqifu/pairlie

[Back-to-Overview]

Image Harmonization/Composition

LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization

• Paper: https://arxiv.org/abs/2304.13166

Semi-supervised Parametric Real-world Image Harmonization

• Paper: https://arxiv.org/abs/2303.00157
• Project: https://kewang0622.github.io/sprih/

PCT-Net: Full Resolution Image Harmonization Using Pixel-Wise Color Transformations

• Paper: CVPR Open Access Version
• Code: https://github.com/rakutentech/PCT-Net-Image-Harmonization/

ObjectStitch: Object Compositing With Diffusion Model

• Paper: CVPR Open Access Version

[Back-to-Overview]

Image Completion/Inpainting

NUWA-LIP: Language-Guided Image Inpainting With Defect-Free VQGAN

• Paper: CVPR Open Access Version
• Code: https://github.com/kodenii/NUWA-LIP

Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting

• Paper: https://arxiv.org/abs/2212.06909

SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model

• Paper: https://arxiv.org/abs/2212.05034

Semi-Supervised Video Inpainting with Cycle Consistency Constraints

• Paper: https://arxiv.org/abs/2208.06807

Deep Stereo Video Inpainting

• Paper: CVPR Open Access Version

[Back-to-Overview]

Image Matting

Referring Image Matting

• Paper: https://arxiv.org/abs/2206.05149
• Code: https://github.com/JizhiziLi/RIM

Adaptive Human Matting for Dynamic Videos

• Paper: https://arxiv.org/abs/2304.06018
• Code: https://github.com/microsoft/AdaM

Mask-Guided Matting in the Wild

• Paper: CVPR Open Access Version

End-to-End Video Matting With Trimap Propagation

• Paper: CVPR Open Access Version
• Code: https://github.com/csvt32745/FTP-VM

Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity

• Paper: CVPR Open Access Version

[Back-to-Overview]

Image Compression

Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger

• Paper: https://arxiv.org/abs/2302.14677

Context-based Trit-Plane Coding for Progressive Image Compression

• Paper: https://arxiv.org/abs/2303.05715
• Code: https://github.com/seungminjeon-github/CTC

Learned Image Compression with Mixed Transformer-CNN Architectures

• Paper: https://arxiv.org/abs/2303.14978
• Code: https://github.com/jmliu206/LIC_TCM

NVTC: Nonlinear Vector Transform Coding

• Paper: https://arxiv.org/abs/2305.16025
• Code: https://github.com/USTC-IMCL/NVTC

Multi-Realism Image Compression with a Conditional Generator

• Paper: https://arxiv.org/abs/2212.13824

LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression

• Paper: https://arxiv.org/abs/2304.12319

Video Compression

Neural Video Compression with Diverse Contexts

• Paper: https://github.com/microsoft/DCVC
• Code: https://arxiv.org/abs/2302.14402

Video Compression With Entropy-Constrained Neural Representations

• Paper: CVPR Open Access Version

Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression

• Paper: CVPR Open Access Version

MMVC: Learned Multi-Mode Video Compression with Block-based Prediction Mode Selection and Density-Adaptive Entropy Coding

• Paper: https://arxiv.org/abs/2304.02273

Motion Information Propagation for Neural Video Compression

• Paper: CVPR Open Access Version

Hierarchical B-Frame Video Coding Using Two-Layer CANF Without Motion Coding

• Paper: CVPR Open Access Version
• Code: https://github.com/nycu-clab/tlzmc-cvpr

HNeRV: A Hybrid Neural Representation for Videos

• Paper: https://arxiv.org/abs/2304.02633
• Code: https://github.com/haochen-rye/HNeRV

[Back-to-Overview]

Image Quality Assessment

Quality-aware Pre-trained Models for Blind Image Quality Assessment

• Paper: https://arxiv.org/abs/2303.00521

Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective

• Paper: https://arxiv.org/abs/2303.14968
• Code: https://github.com/zwx8981/LIQE

Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Method

• Paper: https://arxiv.org/abs/2303.15166
• Code: https://github.com/Dreemurr-T/BAID

Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild

• Paper: https://arxiv.org/abs/2304.00451
• Code: https://github.com/avinabsaha/ReIQA

An Image Quality Assessment Dataset for Portraits

• Paper: https://arxiv.org/abs/2304.05772
• Code: https://github.com/DXOMARK-Research/PIQ2023

MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos

• Paper: CVPR Open Access Version
• Code: https://github.com/zzc-1998/MD-VQA

CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability

• Paper:CVPR Open Access Version
• Code: https://github.com/fdbtrs/CR-FIQA

SB-VQA: A Stack-Based Video Quality Assessment Framework for Video Enhancement

• Paper: https://arxiv.org/abs/2305.08408
• Tags: [Workshop]

[Back-to-Overview]

Style Transfer

Fix the Noise: Disentangling Source Feature for Controllable Domain Translation

• Paper: https://arxiv.org/abs/2303.11545
• Code: https://github.com/LeeDongYeun/FixNoise

Neural Preset for Color Style Transfer

• Paper: https://arxiv.org/abs/2303.13511
• Code: https://github.com/ZHKKKe/NeuralPreset

CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer

• Paper: https://arxiv.org/abs/2303.17867

StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer

• Paper: https://arxiv.org/abs/2304.02744
• Project: https://stylegan-salon.github.io/

Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer

• Paper: https://arxiv.org/abs/2304.04461
• Project: https://kaist-viclab.github.io/old-photo-modernization/

QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity

• Paper: https://arxiv.org/abs/2212.10431
• Code: https://github.com/siyuhuang/QuantArt

Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer

• Paper: https://arxiv.org/abs/2304.11818

Learning Dynamic Style Kernels for Artistic Style Transfer

• Paper: https://arxiv.org/abs/2304.00414

Inversion-Based Style Transfer with Diffusion Models

• Paper: https://arxiv.org/abs/2211.13203
• Code: https://github.com/zyxElsa/InST

[Back-to-Overview]

Image Editing

Imagic: Text-Based Real Image Editing with Diffusion Models

• Paper: https://arxiv.org/abs/2210.09276

SINE: SINgle Image Editing with Text-to-Image Diffusion Models

• Paper: https://arxiv.org/abs/2212.04489
• Code: https://github.com/zhang-zx/SINE

CoralStyleCLIP: Co-optimized Region and Layer Selection for Image Editing

• Paper: https://arxiv.org/abs/2303.05031
• Code: https://github.com/JiauZhang/CoralStyleCLIP

SIEDOB: Semantic Image Editing by Disentangling Object and Background

• Paper: https://arxiv.org/abs/2303.13062
• Code: https://github.com/WuyangLuo/SIEDOB

DiffusionRig: Learning Personalized Priors for Facial Appearance Editing

• Paper: https://arxiv.org/abs/2304.06711
• Code: https://github.com/adobe-research/diffusion-rig

Paint by Example: Exemplar-based Image Editing with Diffusion Models

• Paper: https://arxiv.org/abs/2211.13227
• Code: https://github.com/Fantasy-Studio/Paint-by-Example

StyleRes: Transforming the Residuals for Real Image Editing With StyleGAN

• Paper: https://arxiv.org/abs/2212.14359
• Code: https://github.com/hamzapehlivan/StyleRes

Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint

• Paper: https://arxiv.org/abs/2211.11448
• Code: https://github.com/KumapowerLIU/CLCAE

InstructPix2Pix: Learning to Follow Image Editing Instructions

• Paper: https://arxiv.org/abs/2211.09800
• Code: https://github.com/timothybrooks/instruct-pix2pix

Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model

• Paper: https://arxiv.org/abs/2211.14573

Null-text Inversion for Editing Real Images using Guided Diffusion Models

• Paper: https://arxiv.org/abs/2211.09794
• Code: https://github.com/google/prompt-to-prompt/#null-text-inversion-for-editing-real-images

DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation

• Paper: https://arxiv.org/abs/2303.06285
• Code: https://github.com/Yueming6568/DeltaEdit

Text-Guided Unsupervised Latent Transformation for Multi-Attribute Image Manipulation

• Paper: CVPR Open Access Version

EDICT: Exact Diffusion Inversion via Coupled Transformations

• Paper: https://arxiv.org/abs/2211.12446
• Code: https://github.com/salesforce/EDICT

Video Editing

DPE: Disentanglement of Pose and Expression for General Video Portrait Editing

• Paper: https://arxiv.org/abs/2301.06281
• Code: https://github.com/Carlyx/DPE

Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding

• Paper: https://arxiv.org/abs/2212.02802
• Code: https://github.com/man805/Diffusion-Video-Autoencoders

Shape-aware Text-driven Layered Video Editing

• Paper: https://arxiv.org/abs/2301.13173
• Project: https://text-video-edit.github.io/#

[Back-to-Overview]

Image Generation/Synthesis / Image-to-Image Translation

Text-to-Image / Text Guided / Multi-Modal

GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis

• Paper: https://arxiv.org/abs/2301.12959
• Code: https://github.com/tobran/GALIP

Scaling up GANs for Text-to-Image Synthesis

• Paper: https://arxiv.org/abs/2303.05511
• Project: https://mingukkang.github.io/GigaGAN/

Variational Distribution Learning for Unsupervised Text-to-Image Generation

• Paper: https://arxiv.org/abs/2303.16105

Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation

• Paper: https://arxiv.org/abs/2304.01816

Shifted Diffusion for Text-to-image Generation

• Paper: https://arxiv.org/abs/2211.15388
• Code: https://github.com/drboog/Shifted_Diffusion

ReCo: Region-Controlled Text-to-Image Generation

• Paper: https://arxiv.org/abs/2211.15518
• Code: https://github.com/microsoft/ReCo

RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts

• Paper: CVPR Open Access Version
• Code: https://github.com/WUSTL-CSPL/RIATIG

GLIGEN: Open-Set Grounded Text-to-Image Generation

• Paper: https://arxiv.org/abs/2301.07093
• Code: https://github.com/gligen/GLIGEN

Multi-Concept Customization of Text-to-Image Diffusion

• Paper: https://arxiv.org/abs/2212.04488
• Code: https://github.com/adobe-research/custom-diffusion

ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts

• Paper: CVPR Open Access Version

Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models

• Paper: https://arxiv.org/abs/2212.08698
• Code: https://github.com/UCSB-NLP-Chang/DiffusionDisentanglement

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

• Paper: https://arxiv.org/abs/2208.12242
• Code: https://github.com/google/dreambooth

Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style

• Paper: CVPR Open Access Version
• Code: https://github.com/Picsart-AI-Research/Specialist-Diffusion

MAGVLT: Masked Generative Vision-and-Language Transformer

• Paper: https://arxiv.org/abs/2303.12208

Freestyle Layout-to-Image Synthesis

• Paper: https://arxiv.org/abs/2303.14412
• Code: https://github.com/essunny310/FreestyleNet

Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment

• Paper: https://arxiv.org/abs/2303.17490
• Project: https://sound2scene.github.io/

Collaborative Diffusion for Multi-Modal Face Generation and Editing

• Paper: https://arxiv.org/abs/2304.10530
• Code: https://github.com/ziqihuangg/Collaborative-Diffusion

SpaText: Spatio-Textual Representation for Controllable Image Generation

• Paper: https://arxiv.org/abs/2211.14305

Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation

• Paper: https://arxiv.org/abs/2211.12572
• Code: https://github.com/MichalGeyer/plug-and-play

LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data

• Paper: https://arxiv.org/abs/2208.14889
• Code: https://github.com/KU-CVLAB/LANIT

High-Fidelity Guided Image Synthesis with Latent Diffusion Models

• Paper: https://arxiv.org/abs/2211.17084
• Code: https://github.com/1jsingh/GradOP-Guided-Image-Synthesis

Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

• Paper: https://arxiv.org/abs/2211.05105
• Code: https://github.com/ml-research/safe-latent-diffusion

Image-to-Image / Image Guided

Person Image Synthesis via Denoising Diffusion Model

• Paper: https://arxiv.org/abs/2211.12500
• Code: https://github.com/ankanbhunia/PIDM

Picture that Sketch: Photorealistic Image Generation from Abstract Sketches

• Paper: https://arxiv.org/abs/2303.11162

Fine-Grained Face Swapping via Regional GAN Inversion

• Paper: https://arxiv.org/abs/2211.14068
• Code: https://github.com/e4s2022/e4s

Masked and Adaptive Transformer for Exemplar Based Image Translation

• Paper: https://arxiv.org/abs/2303.17123
• Code: https://github.com/AiArt-HDU/MATEBIT

Zero-shot Generative Model Adaptation via Image-specific Prompt Learning

• Paper: https://arxiv.org/abs/2304.03119
• Code: https://github.com/Picsart-AI-Research/IPL-Zero-Shot-Generative-Model-Adaptation

StyleGene: Crossover and Mutation of Region-Level Facial Genes for Kinship Face Synthesis

• Paper: CVPR Open Access Version
• Code: https://github.com/CVI-SZU/StyleGene

Unpaired Image-to-Image Translation With Shortest Path Regularization

• Paper: CVPR Open Access Version
• Code: https://github.com/Mid-Push/santa

BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models

• Paper: https://arxiv.org/abs/2205.07680
• Code: https://github.com/xuekt98/BBDM

MaskSketch: Unpaired Structure-guided Masked Image Generation

• Paper: https://arxiv.org/abs/2302.05496
• Code: https://github.com/google-research/masksketch

Others for image generation

AdaptiveMix: Improving GAN Training via Feature Space Shrinkage

• Paper: CVPR Open Access Version
• Code: https://github.com/WentianZhang-ML/AdaptiveMix

MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis

• Paper: https://arxiv.org/abs/2211.09117
• Code: https://github.com/LTH14/mage

Regularized Vector Quantization for Tokenized Image Synthesis

• Paper: https://arxiv.org/abs/2303.06424

Exploring Incompatible Knowledge Transfer in Few-shot Image Generation

• Paper: https://arxiv.org/abs/2304.07574
• Code: https://github.com/yunqing-me/RICK

Post-training Quantization on Diffusion Models

• Paper: https://arxiv.org/abs/2211.15736
• Code: https://github.com/42Shawn/PTQ4DM

LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation

• Paper: https://arxiv.org/abs/2303.17189
• Code: https://github.com/ZGCTroy/LayoutDiffusion

DiffCollage: Parallel Generation of Large Content with Diffusion Models

• Paper: https://arxiv.org/abs/2303.17076
• Project: https://research.nvidia.com/labs/dir/diffcollage/

Few-shot Semantic Image Synthesis with Class Affinity Transfer

• Paper: https://arxiv.org/abs/2304.02321

NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs

• Paper: https://arxiv.org/abs/2304.05866
• Code: https://github.com/val-iisc/NoisyTwins

DCFace: Synthetic Face Generation with Dual Condition Diffusion Model

• Paper: https://arxiv.org/abs/2304.07060
• Code: https://github.com/mk-minchul/dcface

Exploring Incompatible Knowledge Transfer in Few-shot Image Generation

• Paper: https://arxiv.org/abs/2304.07574
• Code: https://github.com/yunqing-me/RICK

Class-Balancing Diffusion Models

• Paper: https://arxiv.org/abs/2305.00562

Spider GAN: Leveraging Friendly Neighbors to Accelerate GAN Training

• Paper: https://arxiv.org/abs/2305.07613

Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization

• Paper: https://arxiv.org/abs/2305.11718
• Code: https://github.com/CrossmodalGroup/DynamicVectorQuantization

Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation

• Paper: https://arxiv.org/abs/2305.13607
• Code: https://github.com/CrossmodalGroup/MaskedVectorQuantization

Efficient Scale-Invariant Generator with Column-Row Entangled Pixel Synthesis

• Paper: https://arxiv.org/abs/2303.14157
• Code: https://github.com/VinAIResearch/CREPS

Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis

• Paper: https://arxiv.org/abs/2305.19547
• Code: https://github.com/csyxwei/iPOSE

GLeaD: Improving GANs with A Generator-Leading Task

• Paper: CVPR Open Access Version
• Code: https://github.com/EzioBy/glead

Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization

• Paper: CVPR Open Access Version
• Code: https://github.com/chansey0529/LSO

KD-DLGAN: Data Limited Image Generation via Knowledge Distillation

• Paper: CVPR Open Access Version

Private Image Generation With Dual-Purpose Auxiliary Classifier

• Paper: CVPR Open Access Version

SceneComposer: Any-Level Semantic Image Synthesis

• Paper: https://arxiv.org/abs/2211.11742
• Code: https://github.com/zengxianyu/scenec

Exploring Intra-Class Variation Factors With Learnable Cluster Prompts for Semi-Supervised Image Synthesis

• Paper: CVPR Open Access Version

Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration

• Paper: CVPR Open Access Version
• Code: https://github.com/IntellicentAI-Lab/Re-GAN

Discriminator-Cooperated Feature Map Distillation for GAN Compression

• Paper: https://arxiv.org/abs/2212.14169
• Code: https://github.com/poopit/DCD-official

Wavelet Diffusion Models are fast and scalable Image Generators

• Paper: https://arxiv.org/abs/2211.16152
• Code: https://github.com/VinAIResearch/WaveDiff

On Distillation of Guided Diffusion Models

• Paper: https://arxiv.org/abs/2210.03142

Binary Latent Diffusion

• Paper: https://arxiv.org/abs/2304.04820
• Code: https://github.com/JiauZhang/binary-latent-diffusion

All are Worth Words: A ViT Backbone for Diffusion Models

• Paper: https://arxiv.org/abs/2209.12152
• Code: https://github.com/baofff/U-ViT

Towards Practical Plug-and-Play Diffusion Models

• Paper: https://arxiv.org/abs/2212.05973
• Code: https://github.com/riiid/PPAP

Lookahead Diffusion Probabilistic Models for Refining Mean Estimation

• Paper: https://arxiv.org/abs/2304.11312
• Code: https://github.com/guoqiang-zhang-x/LA-DPM

Diffusion Probabilistic Model Made Slim

• Paper: https://arxiv.org/abs/2211.17106

Self-Guided Diffusion Models

• Paper: https://arxiv.org/abs/2210.06462

Video Generation

Conditional Image-to-Video Generation with Latent Flow Diffusion Models

• Paper: https://arxiv.org/abs/2303.13744
• Code: https://github.com/nihaomiao/CVPR2023_LFDM

Video Probabilistic Diffusion Models in Projected Latent Space

• Paper: https://arxiv.org/abs/2302.07685
• Code: https://github.com/sihyun-yu/PVDM

Decomposed Diffusion Models for High-Quality Video Generation

• Paper: https://arxiv.org/abs/2303.08320

MoStGAN: Video Generation with Temporal Motion Styles

• Paper: https://arxiv.org/abs/2304.02777
• Code: https://github.com/xiaoqian-shen/MoStGAN

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models

• Paper: https://arxiv.org/abs/2304.08818

Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation

• Paper: https://arxiv.org/abs/2211.12824
• Code: https://github.com/tsujuifu/pytorch_tvc

MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation

• Paper: CVPR Open Access Version
• Code: https://github.com/researchmm/MM-Diffusion

Dimensionality-Varying Diffusion Process

• Paper: https://arxiv.org/abs/2211.16032

[Back-to-Overview]

Others

Perspective Fields for Single Image Camera Calibration

• Paper: https://arxiv.org/abs/2212.03239
• Code: https://github.com/jinlinyi/PerspectiveFields

DC2: Dual-Camera Defocus Control by Learning to Refocus

• Paper: https://arxiv.org/abs/2304.03285
• Project: https://defocus-control.github.io/

Images Speak in Images: A Generalist Painter for In-Context Visual Learning

• Paper: https://arxiv.org/abs/2212.02499
• Code: https://github.com/baaivision/Painter

Make-A-Story: Visual Memory Conditioned Consistent Story Generation

• Paper: https://arxiv.org/abs/2211.13319
• Code: https://github.com/ubc-vision/Make-A-Story

Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences between Pretrained Generative Models

• Paper: https://arxiv.org/abs/2303.10774
• Code: https://github.com/mattolson93/cross_gan_auditing

LightPainter: Interactive Portrait Relighting with Freehand Scribble

• Paper: https://arxiv.org/abs/2303.12950
• Tags: Portrait Relighting

Neural Texture Synthesis with Guided Correspondence

• Paper: CVPR Open Access Version
• Code: https://github.com/EliotChenKJ/Guided-Correspondence-Loss
• Tags: Texture Synthesis

Uncurated Image-Text Datasets: Shedding Light on Demographic Bias

• Paper: https://arxiv.org/abs/2304.02828
• Code: https://github.com/noagarcia/phase

Large-capacity and Flexible Video Steganography via Invertible Neural Network

• Paper: https://arxiv.org/abs/2304.12300
• Code: https://github.com/MC-E/LF-VSN
• Tags: Steganography

Putting People in Their Place: Affordance-Aware Human Insertion into Scenes

• Paper: https://arxiv.org/abs/2304.14406
• Code: https://github.com/adobe-research/affordance-insertion

Controllable Light Diffusion for Portraits

• Paper: https://arxiv.org/abs/2305.04745
• Tags: Relighting

Talking Head Generation

Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert

• Paper: https://arxiv.org/abs/2303.17480
• Code: https://github.com/Sxjdwang/TalkLip

High-Fidelity and Freely Controllable Talking Head Video Generation

• Paper: https://arxiv.org/abs/2304.10168
• Code: https://github.com/hologerry/PECHead

MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation

• Paper: https://arxiv.org/abs/2212.08062
• Code: https://github.com/Meta-Portrait/MetaPortrait

Identity-Preserving Talking Face Generation with Landmark and Appearance Priors

• Paper: https://arxiv.org/abs/2305.08293
• Code: https://github.com/Weizhi-Zhong/IP_LAP

LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook

• Paper: CVPR Open Access Version

High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning

• Paper: https://arxiv.org/abs/2305.02572

DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation

• Paper: https://arxiv.org/abs/2301.03786
• Code: https://github.com/sstzal/DiffTalk

Virtual Try-on

GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning

• Paper: https://arxiv.org/abs/2303.13756
• Code: https://github.com/xiezhy6/GP-VTON

Linking Garment With Person via Semantically Associated Landmarks for Virtual Try-On

• Paper: CVPR Open Access Version
• Code: https://modelscope.cn/datasets/damo/SAL-HG/summary

TryOnDiffusion: A Tale of Two UNets

• Paper: https://openaccess.thecvf.com/content/CVPR2023/html/Zhu_TryOnDiffusion_A_Tale_of_Two_UNets_CVPR_2023_paper.html

Handwriting/Font Generation

CF-Font: Content Fusion for Few-shot Font Generation

• Paper: https://arxiv.org/abs/2303.14017
• Code: https://github.com/wangchi95/CF-Font
• Tags: Font Generation

Neural Transformation Fields for Arbitrary-Styled Font Generation

• Paper: CVPR Open Access Version
• Code: https://github.com/fubinfb/NTF

DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality

• Paper: https://arxiv.org/abs/2303.14585
• Code: https://github.com/yizhiwang96/deepvecfont-v2

Handwritten Text Generation from Visual Archetypes

• Paper: https://arxiv.org/abs/2303.15269
• Tags: Handwriting Generation

Disentangling Writer and Character Styles for Handwriting Generation

• Paper: https://arxiv.org/abs/2303.14736
• Code: https://github.com/dailenson/SDT
• Tags: Handwriting Generation

Conditional Text Image Generation With Diffusion Models

• Paper: CVPR Open Access Version

Layout Generation

Unifying Layout Generation with a Decoupled Diffusion Model

• Paper: https://arxiv.org/abs/2303.05049

Unsupervised Domain Adaption with Pixel-level Discriminator for Image-aware Layout Generation

• Paper: https://arxiv.org/abs/2303.14377

PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout

• Paper: https://arxiv.org/abs/2303.15937
• Code: https://github.com/PKU-ICST-MIPL/PosterLayout-CVPR2023

LayoutDM: Discrete Diffusion Model for Controllable Layout Generation

• Paper: https://arxiv.org/abs/2303.08137
• Code: https://github.com/CyberAgentAILab/layout-dm

LayoutDM: Transformer-based Diffusion Model for Layout Generation

• Paper: https://arxiv.org/abs/2305.02567