AAAI2022-Low-Level-Vision.md

Awesome-AAAI2022-Low-Level-Vision

A Collection of Papers and Codes in AAAI2022 related to Low-Level Vision

Related collections for low-level vision

• CVPR2022-Low-Level-Vision
• Awesome-NeurIPS2021-Low-Level-Vision
• Awesome-ICCV2021-Low-Level-Vision
• Awesome-CVPR2021/CVPR2020-Low-Level-Vision
• Awesome-ECCV2020-Low-Level-Vision

Catalogue

• 1.Image Restoration

  • Burst Restoration
  • Video Restoration

• 2.Super Resolution

  • Image Super Resolution
  • Video Super Resolution

• 3.Image Rescaling

• 4.Denoising

  • Image Denoising
  • Video Denoising

• 5.Deblurring

  • Image Deblurring
  • Video Deblurring

• 6.Deraining

• 7.Dehazing

• 8.Demosaicing

• 9.HDR Imaging / Multi-Exposure Image Fusion

• 10.Frame Interpolation

• 11.Image Enhancement

  • Low-Light Image Enhancement

• 12.Image Harmonization

• 13.Image Completion/Inpainting

• 14.Image Matting

• 15.Shadow Removal

• 16.Image Compression

• 17.Image Quality Assessment

• 18.Style Transfer

• 19.Image Editing

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

  • Video Generation

Image Restoration - 图像恢复

Unsupervised Underwater Image Restoration: From a Homology Perspective

• Paper: https://aaai-2022.virtualchair.net/poster_aaai2078
• Tags: Underwater Image Restoration

Panini-Net: GAN Prior based Degradation-Aware Feature Interpolation for Face Restoration

• Paper: https://aaai-2022.virtualchair.net/poster_aaai4252
• Code: https://github.com/wyhuai/Panini-Net
• Tags: Face Restoration

Burst Restoration

Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers

• Paper: https://aaai-2022.virtualchair.net/poster_aaai7488
• Code: https://github.com/laulampaul/siamtrans

Video Restoration

Transcoded Video Restoration by Temporal Spatial Auxiliary Network

• Paper: https://aaai-2022.virtualchair.net/poster_aaai12302
• Tags: Transcoded Video Restoration

Super Resolution - 超分辨率

Image Super Resolution

SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution

• Paper: https://aaai-2022.virtualchair.net/poster_aaai528

Efficient Non-Local Contrastive Attention for Image Super-Resolution

• Paper: https://arxiv.org/abs/2201.03794
• Code: https://github.com/Zj-BinXia/ENLCA

Best-Buddy GANs for Highly Detailed Image Super-Resolution

• Paper: https://aaai-2022.virtualchair.net/poster_aaai137
• Tags: GAN

Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution

• Paper: https://aaai-2022.virtualchair.net/poster_aaai1194
• Tags: Text SR

Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-Based Super-Resolution

• Paper: https://aaai-2022.virtualchair.net/poster_aaai390
• Code: https://github.com/Zj-BinXia/AMSA
• Tags: Reference-Based SR

Detail-Preserving Transformer for Light Field Image Super-Resolution

• Paper: https://aaai-2022.virtualchair.net/poster_aaai3550
• Tags: Light Field

Video Super Resolution

Image Rescaling - 图像缩放

Denoising - 去噪

Image Denoising

Generative Adaptive Convolutions for Real-World Noisy Image Denoising

• Paper: https://aaai-2022.virtualchair.net/poster_aaai4230

Video Denoising

ReMoNet: Recurrent Multi-Output Network for Efficient Video Denoising

• Paper: https://aaai-2022.virtualchair.net/poster_aaai6295

Deblurring - 去模糊

Image Deblurring

Video Deblurring

Deep Recurrent Neural Network with Multi-Scale Bi-Directional Propagation for Video Deblurring

• Paper: https://aaai-2022.virtualchair.net/poster_aaai3124

Deraining - 去雨

Online-Updated High-Order Collaborative Networks for Single Image Deraining

• Paper: https://aaai-2022.virtualchair.net/poster_aaai6295

Close the Loop: A Unified Bottom-up and Top-down Paradigm for Joint Image Deraining and Segmentation

• Paper: https://aaai-2022.virtualchair.net/poster_aaai678
• Tags: Joint Image Deraining and Segmentation

Dehazing - 去雾

Uncertainty-Driven Dehazing Network

• Paper: https://aaai-2022.virtualchair.net/poster_aaai2838

Demosaicing - 去马赛克

Deep Spatial Adaptive Network for Real Image Demosaicing

• Paper: https://aaai-2022.virtualchair.net/poster_aaai2170

HDR Imaging / Multi-Exposure Image Fusion - HDR图像生成 / 多曝光图像融合

TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework Using Self-Supervised Multi-Task Learning

• Paper: https://arxiv.org/abs/2112.01030
• Code: https://github.com/miccaiif/TransMEF

Frame Interpolation - 插帧

Image Enhancement - 图像增强

Low-Light Image Enhancement

Low-Light Image Enhancement with Normalizing Flow

• Paper: https://arxiv.org/abs/2109.05923
• Code: https://github.com/wyf0912/LLFlow

Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement

• Paper: https://aaai-2022.virtualchair.net/poster_aaai841

Semantically Contrastive Learning for Low-Light Image Enhancement

• Paper: https://aaai-2022.virtualchair.net/poster_aaai4218
• Tags: contrastive learning

Image Harmonization/Composition - 图像协调/图像合成

Image Completion/Inpainting - 图像修复

Image Matting - 图像抠图

MODNet: Trimap-Free Portrait Matting in Real Time

• Paper: https://arxiv.org/abs/2011.11961
• Code: https://github.com/ZHKKKe/MODNet

Shadow Removal - 阴影消除

Efficient Model-Driven Network for Shadow Removal

• Paper: https://aaai-2022.virtualchair.net/poster_aaai196

Image Compression - 图像压缩

Towards End-to-End Image Compression and Analysis with Transformers

• Paper: https://arxiv.org/abs/2112.09300
• Code: https://github.com/BYchao100/Towards-Image-Compression-and-Analysis-with-Transformers
• Tags: Transformer

OoDHDR-Codec: Out-of-Distribution Generalization for HDR Image Compression

• Paper: https://aaai-2022.virtualchair.net/poster_aaai8610

Two-Stage Octave Residual Network for End-to-End Image Compression

• Paper: https://aaai-2022.virtualchair.net/poster_aaai4043

Image Quality Assessment - 图像质量评价

Content-Variant Reference Image Quality Assessment via Knowledge Distillation

• Paper: https://aaai-2022.virtualchair.net/poster_aaai1344

Perceptual Quality Assessment of Omnidirectional Images

• Paper: https://aaai-2022.virtualchair.net/poster_aaai4008
• Tags: Omnidirectional Images

Style Transfer - 风格迁移

Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization

• Paper: https://arxiv.org/abs/2103.11784
• Code: https://github.com/czczup/URST

Deep Translation Prior: Test-Time Training for Photorealistic Style Transfer

• Paper: https://aaai-2022.virtualchair.net/poster_aaai1958

Image Editing - 图像编辑

Image Generation/Synthesis / Image-to-Image Translation - 图像生成/合成/转换

SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal

• Paper: https://aaai-2022.virtualchair.net/poster_aaai934
• Code: https://github.com/Snowfallingplum/SSAT
• Tags: Makeup Transfer and Removal

Assessing a Single Image in Reference-Guided Image Synthesis

• Paper: https://aaai-2022.virtualchair.net/poster_aaai1241

Interactive Image Generation with Natural-Language Feedback

• Paper: https://aaai-2022.virtualchair.net/poster_aaai7081

PetsGAN: Rethinking Priors for Single Image Generation

• Paper: https://aaai-2022.virtualchair.net/poster_aaai2865

Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction

• Paper: https://aaai-2022.virtualchair.net/poster_aaai4099

Hierarchical Image Generation via Transformer-Based Sequential Patch Selection

• Paper: https://aaai-2022.virtualchair.net/poster_aaai557

Style-Guided and Disentangled Representation for Robust Image-to-Image Translation

• Paper: https://aaai-2022.virtualchair.net/poster_aaai3727

OA-FSUI2IT: A Novel Few-Shot Cross Domain Object Detection Framework with Object-Aware Few-shot Unsupervised Image-to-Image Translation

• Paper: https://aaai-2022.virtualchair.net/poster_aaai2213
• Code: https://github.com/emdata-ailab/FSCD-Det
• Tags: Image-to-Image Translation used for Object Detection

Video Generation

Learning Temporally and Semantically Consistent Unpaired Video-to-Video Translation through Pseudo-Supervision from Synthetic Optical Flow

• Paper: https://aaai-2022.virtualchair.net/poster_aaai4610
• Code: https://github.com/wangkaihong/Unsup_Recycle_GAN