Luciennnnnnn / Awesome-ICCV2023-Low-Level-Vision

A Collection of Papers and Codes in ICCV2023/2021 about low level vision

Awesome-ICCV2023-Low-Level-Vision

A Collection of Papers and Codes in ICCV2023 related to Low-Level Vision

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

Related collections for low-level vision

• Awesome-ICCV2021-Low-Level-Vision
• Awesome-CVPR2023/2022-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

Multi-weather Image Restoration via Domain Translation

• Paper:
• Code: https://github.com/pwp1208/Domain_Translation_Multi-weather_Restoration
• Tags: Multi-weather

Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond

• Paper: https://arxiv.org/abs/2307.08996
• Tags: Authentic Face Restoration, Diffusion

Physics-Driven Turbulence Image Restoration with Stochastic Refinement

• Paper: https://arxiv.org/abs/2307.10603
• Code: https://github.com/VITA-Group/PiRN
• Tags: Turbulence Image

[Back-to-Overview]

Super Resolution

Image Super Resolution

On the Effectiveness of Spectral Discriminators for Perceptual Quality Improvement

• Paper: https://arxiv.org/abs/2307.12027
• Code: https://github.com/Luciennnnnnn/DualFormer

SRFormer: Permuted Self-Attention for Single Image Super-Resolution

• Paper: https://arxiv.org/abs/2303.09735
• Code: https://github.com/HVision-NKU/SRFormer

Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution

• Paper: https://arxiv.org/abs/2303.08942
• Code: https://github.com/Zhaozixiang1228/GDSR-SSDNet

Diffir: Efficient diffusion model for image restoration

• Paper:
• Code: https://github.com/Zj-BinXia/DiffIR

Spatial-Temporal Video Super-Resolution

MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution

• Paper: https://arxiv.org/abs/2307.07988
• Code: https://github.com/sichun233746/MoTIF

[Back-to-Overview]

Denoising - 去噪 [back]

Image Denoising

Random Sub-Samples Generation for Self-Supervised Real Image Denoising

• Paper:
• Code: https://github.com/p1y2z3/SDAP

The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior

• Paper: https://arxiv.org/abs/2304.11409
• Code: https://github.com/YilinLiu97/FasterDIP-devil-in-upsampling

Hybrid Spectral Denoising Transformer with Learnable Query

• Paper: https://arxiv.org/abs/2303.09040
• Code: https://github.com/Zeqiang-Lai/HSDT
• Tags: hyperspectral image denoising

[Back-to-Overview]

Image Enhancement

Low-Light Image Enhancement

ExposureDiffusion: Learning to Expose for Low-light Image Enhancement

• Paper: https://arxiv.org/abs/2307.07710

Implicit Neural Representation for Cooperative Low-light Image Enhancement

• Paper: https://arxiv.org/abs/2303.11722
• Code: https://github.com/Ysz2022/NeRCo

[Back-to-Overview]

Image Harmonization/Composition

Deep Image Harmonization with Learnable Augmentation

• Paper:
• Code: https://github.com/bcmi/SycoNet-Adaptive-Image-Harmonization

[Back-to-Overview]

Image Stitching

Parallax-Tolerant Unsupervised Deep Image Stitching

• Paper:
• Code: https://github.com/nie-lang/UDIS2

[Back-to-Overview]

Image Quality Assessment

Delegate Transformer for Image Color Aesthetics Assessment

• Paper:
• Code: https://github.com/woshidandan/Image-Color-Aesthetics-Assessment/tree/main

Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives

• Paper https://arxiv.org/abs/2211.04894
• Code: https://github.com/VQAssessment/DOVER

[Back-to-Overview]

Style Transfer

AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks

• Paper: https://arxiv.org/abs/2307.09724
• Code: https://github.com/Kibeom-Hong/AesPA-Net

Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers

• Paper:
• Code: https://github.com/NevSNev/UniST

[Back-to-Overview]

Image Editing

Adaptive Nonlinear Latent Transformation for Conditional Face Editing

• Paper: https://arxiv.org/abs/2307.07790
• Code: https://github.com/Hzzone/AdaTrans

Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing

• Paper: https://arxiv.org/abs/2304.02051
• Code: https://github.com/aimagelab/multimodal-garment-designer

MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing

• Paper: https://arxiv.org/abs/2304.08465
• Code: https://github.com/TencentARC/MasaCtrl

Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation

• Paper: https://arxiv.org/abs/2307.08448
• Code: https://github.com/AndysonYs/Selective-Diffusion-Distillation

HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending

• Paper:
• Code: https://github.com/wty-ustc/HairCLIPv2

[Back-to-Overview]

Image Generation/Synthesis / Image-to-Image Translation

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

MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models

• Paper: https://arxiv.org/abs/2303.13126
• Code: https://github.com/MagicFusion/MagicFusion.github.io

ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation

• Paper: https://arxiv.org/abs/2302.13848
• Code: https://github.com/csyxwei/ELITE

Better Aligning Text-to-Image Models with Human Preference

• Paper: https://arxiv.org/abs/2303.14420
• Code: https://github.com/tgxs002/align_sd

Unleashing Text-to-Image Diffusion Models for Visual Perception

• Paper: https://arxiv.org/abs/2303.02153
• Code: https://github.com/wl-zhao/VPD

Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models

• Paper: https://arxiv.org/abs/2306.05357
• Code: https://github.com/nanlliu/Unsupervised-Compositional-Concepts-Discovery

BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

• Paper: https://arxiv.org/abs/2307.10816
• Code: https://github.com/Sierkinhane/BoxDiff

Ablating Concepts in Text-to-Image Diffusion Models

• Paper: https://arxiv.org/abs/2303.13516
• Code: https://github.com/nupurkmr9/concept-ablation

Image-to-Image / Image Guided

Reinforced Disentanglement for Face Swapping without Skip Connection

• Paper: https://arxiv.org/abs/2307.07928

BlendFace: Re-designing Identity Encoders for Face-Swapping

• Paper: https://arxiv.org/abs/2307.10854
• Code: https://github.com/mapooon/BlendFace

Others for image generation

Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decoration

• Paper: https://arxiv.org/abs/2307.09621

Masked Diffusion Transformer is a Strong Image Synthesizer

• Paper: https://arxiv.org/abs/2303.14389
• Code: https://github.com/sail-sg/MDT

Q-Diffusion: Quantizing Diffusion Models

• Paper: https://arxiv.org/abs/2302.04304
• Code: https://github.com/Xiuyu-Li/q-diffusion

Video Generation

Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer

• Paper: https://arxiv.org/abs/2307.07754
• Code: https://github.com/rocketappslab/bdmm

MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions

• Paper: https://arxiv.org/abs/2307.10008
• Code: https://github.com/DreamtaleCore/MODA

Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators

• Paper: https://arxiv.org/abs/2303.13439
• Code: https://github.com/Picsart-AI-Research/Text2Video-Zero

FateZero: Fusing Attentions for Zero-shot Text-based Video Editing

• Paper: https://arxiv.org/abs/2303.09535
• Code: https://github.com/ChenyangQiQi/FateZero

[Back-to-Overview]

Others [back]

DDColor: Towards Photo-Realistic and Semantic-Aware Image Colorization via Dual Decoders

• Paper: https://arxiv.org/abs/2212.11613
• Code: https://github.com/piddnad/DDColor
• Tags: Colorization

DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion

• Paper: https://arxiv.org/abs/2303.06840
• Code: https://github.com/Zhaozixiang1228/MMIF-DDFM
• Tags: Image Fusion

Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer

• Paper: https://arxiv.org/abs/2212.03434
• Code: https://github.com/ryeocthiv/CQFormer

Talking Head Generation

Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation

• Paper: https://arxiv.org/abs/2307.09906
• Code: https://github.com/harlanhong/ICCV2023-MCNET