hust-lidelong / CVPR2022-Low-Level-Vision

A Collection of Papers and Codes in CVPR2022 about low level vision

CVPR2022-Low-Level-Vision

A Collection of Papers and Codes in CVPR2022 related to Low-Level Vision

Related collections for low-level vision

• Awesome-ICCV2021-Low-Level-Vision
• Awesome-CVPR2021/CVPR2020-Low-Level-Vision
• Awesome-ECCV2020-Low-Level-Vision

• Image Restoration

  • Burst Restoration
  • Video Restoration

• Super Resolution

  • Image Super Resolution
  • Video Super Resolution

• Image Rescaling

• Denoising

• Image Completion/Inpainting

• Image Compression

• Style Transfer

• Image Editing

Image Restoration - 图像恢复

Restormer: Efficient Transformer for High-Resolution Image Restoration

• Paper: https://arxiv.org/abs/2111.09881
• Code: https://github.com/swz30/Restormer
• Tags: Transformer

Uformer: A General U-Shaped Transformer for Image Restoration

• Paper: https://arxiv.org/abs/2106.03106
• Code: https://github.com/ZhendongWang6/Uformer
• Tags: Transformer

All-In-One Image Restoration for Unknown Corruption

• Paper: http://pengxi.me/wp-content/uploads/2022/03/All-In-One-Image-Restoration-for-Unknown-Corruption.pdf
• Code: https://github.com/XLearning-SCU/2022-CVPR-AirNet

Fourier Document Restoration for Robust Document Dewarping and Recognition

• Paper: https://arxiv.org/abs/2203.09910
• Tags: Document Restoration

Burst Restoration

A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift

• Paper: https://arxiv.org/abs/2203.09294
• Code: https://github.com/GuoShi28/2StageAlign
• Tags: joint denoising and demosaicking

Video Restoration

Neural Compression-Based Feature Learning for Video Restoration

• Paper:https://arxiv.org/abs/2203.09208

Super Resolution - 超分辨率

Image Super Resolution

Reflash Dropout in Image Super-Resolution

• Paper: https://arxiv.org/abs/2112.12089
• Code: https://github.com/Xiangtaokong/Reflash-Dropout-in-Image-Super-Resolution

Learning the Degradation Distribution for Blind Image Super-Resolution

• Paper: https://arxiv.org/abs/2203.04962
• Code: https://github.com/greatlog/UnpairedSR
• Tags: Blind SR

Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution

• Paper: https://arxiv.org/abs/2203.09195
• Code: https://github.com/csjliang/LDL
• Tags: Real SR

GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors

• Paper: https://arxiv.org/abs/2203.07319
• Tags: Face SR

A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution

• Paper: https://arxiv.org/abs/2203.09388
• Code: https://github.com/mjq11302010044/TATT
• Tags: Text SR

Video Super Resolution

BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment

• Paper: https://arxiv.org/abs/2104.13371
• Code: https://github.com/ckkelvinchan/BasicVSR_PlusPlus

Image Rescaling - 图像缩放

Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence

• Paper: https://arxiv.org/abs/2203.00911

Denoising - 去噪

Self-Supervised Image Denoising via Iterative Data Refinement

• Paper: https://arxiv.org/abs/2111.14358
• Code: https://github.com/zhangyi-3/IDR
• Tags: Self-Supervised

Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots

• Paper: https://arxiv.org/abs/2203.06967
• Code: https://github.com/demonsjin/Blind2Unblind
• Tags: Self-Supervised

Image Completion/Inpainting - 图像修复

Bridging Global Context Interactions for High-Fidelity Image Completion

• Paper: https://arxiv.org/abs/2104.00845
• Code: https://github.com/lyndonzheng/TFill

Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding

• Paper: https://arxiv.org/abs/2203.00867
• Code: https://github.com/DQiaole/ZITS_inpainting

MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting

• Paper: https://arxiv.org/abs/2203.06304
• Code: https://github.com/tsingqguo/misf

Image Compression - 图像压缩

Neural Data-Dependent Transform for Learned Image Compression

• Paper: https://arxiv.org/abs/2203.04963v1

The Devil Is in the Details: Window-based Attention for Image Compression

• Paper: https://arxiv.org/abs/2203.08450
• Code: https://github.com/Googolxx/STF

ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding

• Paper: https://arxiv.org/abs/2203.10886

Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression

• Paper: https://arxiv.org/abs/2203.10897

Style Transfer - 风格迁移

CLIPstyler: Image Style Transfer with a Single Text Condition

• Paper: https://arxiv.org/abs/2112.00374
• Code: https://github.com/cyclomon/CLIPstyler
• Tags: CLIP

Style-ERD: Responsive and Coherent Online Motion Style Transfer

• Paper: https://arxiv.org/abs/2203.02574
• Code: https://github.com/tianxintao/Online-Motion-Style-Transfer

Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization

• Paper: https://arxiv.org/abs/2203.07740
• Code: https://github.com/YBZh/EFDM

Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer

• Paper:
• Code: https://github.com/williamyang1991/DualStyleGAN

Image Editing - 图像编辑

High-Fidelity GAN Inversion for Image Attribute Editing

• Paper: https://arxiv.org/abs/2109.06590
• Code: https://github.com/Tengfei-Wang/HFGI

Style Transformer for Image Inversion and Editing

• Paper: https://arxiv.org/abs/2203.07932
• Code: https://github.com/sapphire497/style-transformer

HairCLIP: Design Your Hair by Text and Reference Image

• Paper: https://arxiv.org/abs/2112.05142
• Code: https://github.com/wty-ustc/HairCLIP
• Tags: CLIP

HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing

• Paper: https://arxiv.org/abs/2111.15666
• Code: https://github.com/yuval-alaluf/hyperstyle

Blended Diffusion for Text-driven Editing of Natural Images

• Paper: https://arxiv.org/abs/2111.14818
• Code: https://github.com/omriav/blended-diffusion
• Tags: CLIP

FlexIT: Towards Flexible Semantic Image Translation

• Paper: https://arxiv.org/abs/2203.04705

SemanticStyleGAN: Learning Compositonal Generative Priors for Controllable Image Synthesis and Editing

• Paper: https://arxiv.org/abs/2112.02236