Awesome

Awesome-AAAI2023-Low-Level-Vision

A Collection of Papers and Codes in AAAI2023 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-AAAI2022-Low-Level-Vision
• Awesome-NeurIPS2023~2021-Low-Level-Vision
• Awesome-ICCV2023/2021-Low-Level-Vision
• Awesome-CVPR2023/2022-Low-Level-Vision
• Awesome-ECCV2022-Low-Level-Vision
• Awesome-CVPR2021/2020-Low-Level-Vision
• Awesome-ECCV2020-Low-Level-Vision

Overview

• Image Restoration

• Super Resolution

• Image Rescaling

• Denoising

  • Image Denoising
  • Video 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

<a name="ImageRetoration"></a>

Image Restoration

Memory-Oriented Structural Pruning for Efficient Image Restoration

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25319

ShadowFormer: Global Context Helps Shadow Removal

• Paper: https://arxiv.org/abs/2302.01650
• Code: https://github.com/GuoLanqing/ShadowFormer
• Tags: Shadow Removal

DENet: Disentangled Embedding Network for Visible Watermark Removal

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25337
• Code: https://github.com/lianchengmingjue/DENet
• Tags: Watermark Removal

Video Compression Artifact Reduction by Fusing Motion Compensation and Global Context in a Swin-CNN Based Parallel Architecture

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25458

Image Reconstruction

[Back-to-Overview]

<a name="SuperResolution"></a>

Super Resolution

Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25409
• Code: https://github.com/xiaogang00/DP3DF

[Back-to-Overview]

<a name="Rescaling"></a>

Image Rescaling

Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

• Paper: https://arxiv.org/abs/2303.02353
• Code: https://github.com/yang-jin-hai/SAIN

[Back-to-Overview]

<a name="Denoising"></a>

Denoising

Image Denoising

Adaptive Dynamic Filtering Network for Image Denoising

• Paper: https://arxiv.org/abs/2211.12051
• Code: https://github.com/it-hao/ADFNet

Self-Supervised Image Denoising Using Implicit Deep Denoiser Prior

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25245
• Tags: Self-Supervised

Robust Image Denoising of No-Flash Images Guided by Consistent Flash Images

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25291
• Code: https://github.com/CGLab-GIST/RIDFnF

Spatial-Spectral Transformer for Hyperspectral Image Denoising

• Paper: https://arxiv.org/abs/2211.14090
• Code: https://github.com/MyuLi/SST
• Tags: Hyperspectral

Video Denoising

Unsupervised Deep Video Denoising with Untrained Network

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25476

[Back-to-Overview]

<a name="Deblurring"></a>

Deblurring

<a name="ImageDeblurring"></a>

Image Deblurring

Dual-Domain Attention for Image Deblurring

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25122

Real-World Deep Local Motion Deblurring

• Paper: https://arxiv.org/abs/2204.08179
• Code: https://github.com/LeiaLi/ReLoBlur

Learning Single Image Defocus Deblurring with Misaligned Training Pairs

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25235
• Code: https://github.com/liyucs/JDRL

Intriguing Findings of Frequency Selection for Image Deblurring

• Paper: https://arxiv.org/abs/2111.11745
• Code: https://github.com/INVOKERer/DeepRFT/tree/AAAI2023

Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25446

[Back-to-Overview]

<a name="Deraining"></a>

Deraining

Hybrid CNN-Transformer Feature Fusion for Single Image Deraining

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25111
• Code: https://github.com/cschenxiang/HCT-FFN

[Back-to-Overview]

<a name="HDR"></a>

HDR Imaging / Multi-Exposure Image Fusion

Improving Dynamic HDR Imaging with Fusion Transformer

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25107

Unsupervised Multi-Exposure Image Fusion Breaking Exposure Limits via Contrastive Learning

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25404
• Code: https://github.com/hanna-xu/MEF-CL [404]

[Back-to-Overview]

<a name="FrameInterpolation"></a>

Frame Interpolation

SVFI: Spiking-Based Video Frame Interpolation for High-Speed Motion

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25393

[Back-to-Overview]

<a name="Enhancement"></a>

Image Enhancement

Polarization-Aware Low-Light Image Enhancement

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25486
• Code: https://github.com/fourson/Polarization-Aware-Low-Light-Image-Enhancement

Learning Semantic Degradation-Aware Guidance for Recognition-Driven Unsupervised Low-Light Image Enhancement

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25479
• Code: https://github.com/zheng980629/SDAG

Low-Light Image Enhancement Network Based on Multi-Scale Feature Complementation

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25427

Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method

• Paper: https://arxiv.org/abs/2212.11548
• Code: https://github.com/TaoWangzj/LLFormer

Low-Light Video Enhancement with Synthetic Event Guidance

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25257
• Code: https://gitee.com/mindspore/models/tree/master/research/cv/LLVE-SEG [404]

[Back-to-Overview]

<a name="Harmonization"></a>

Image Harmonization/Composition

Painterly Image Harmonization in Dual Domains

• Paper: https://arxiv.org/abs/2212.08846
• Code: https://github.com/bcmi/PHDNet-Painterly-Image-Harmonization

[Back-to-Overview]

<a name="Inpainting"></a>

Image Completion/Inpainting

CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying

• Paper: https://arxiv.org/abs/2303.08524
• Code: https://github.com/NiFangBaAGe/CoordFill

Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning

• Paper: https://arxiv.org/abs/2303.13133
• Code: https://github.com/zzw-zjgsu/Generative-Image-Inpainting

DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25464
• Code: https://github.com/MRzzm/DINet

[Back-to-Overview]

<a name="Matting"></a>

Image Matting

Infusing Definiteness into Randomness: Rethinking Composition Styles for Deep Image Matting

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25432
• Code: https://github.com/coconuthust/composition_styles

[Back-to-Overview]

<a name="ImageCompression"></a>

Image Compression

Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25551

Multi-Modality Deep Network for Extreme Learned Image Compression

• Paper: https://arxiv.org/abs/2304.13583

[Back-to-Overview]

<a name="ImageQualityAssessment"></a>

Image Quality Assessment

Data-Efficient Image Quality Assessment with Attention-Panel Decoder

• Paper: https://arxiv.org/abs/2304.04952
• Code: https://github.com/narthchin/DEIQT

[Back-to-Overview]

<a name="StyleTransfer"></a>

Style Transfer

User-Controllable Arbitrary Style Transfer via Entropy Regularization

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25117
• Code: https://github.com/cplusx/eps-Assign-and-Mix

Frequency Domain Disentanglement for Arbitrary Neural Style Transfer

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25212

AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-Realistic Style Transfer

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25248

Preserving Structural Consistency in Arbitrary Artist and Artwork Style Transfer

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25384

MicroAST: Towards Super-fast Ultra-Resolution Arbitrary Style Transfer

• Paper: https://arxiv.org/abs/2211.15313
• Code: https://github.com/EndyWon/MicroAST

[Back-to-Overview]

<a name="ImageEditing"></a>

Image Editing

DE-net: Dynamic Text-Guided Image Editing Adversarial Networks

• Paper: https://arxiv.org/abs/2206.01160
• Code: https://github.com/tobran/DE-Net

FEditNet: Few-Shot Editing of Latent Semantics in GAN Spaces

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25394
• Code: https://github.com/THU-LYJ-Lab/FEditNet

ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing

• Paper: https://arxiv.org/abs/2301.13402

Target-Free Text-Guided Image Manipulation

• Paper: https://arxiv.org/abs/2211.14544

CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics

• Paper: https://arxiv.org/abs/2212.02122
• Code: https://github.com/NetEase-GameAI/clipvg

[Back-to-Overview]

<a name=ImageGeneration></a>

Image Generation/Synthesis / Image-to-Image Translation

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

Reject Decoding via Language-Vision Models for Text-to-Image Synthesis

• Paper: MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-robust Classifier

Scene Graph to Image Synthesis via Knowledge Consensus

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25387

Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis

• Paper: https://arxiv.org/abs/2208.13753
• Code: https://github.com/davidhalladay/Frido

Image-to-Image / Image Guided

MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier

• Paper: https://arxiv.org/abs/2209.11549
• Code: https://github.com/mozhdehrouhsedaghat/magic

CFFT-GAN: Cross-Domain Feature Fusion Transformer for Exemplar-Based Image Translation

• Paper: https://arxiv.org/abs/2302.01608

MIDMs: Matching Interleaved Diffusion Models for Exemplar-based Image Translation

• Paper: https://arxiv.org/abs/2209.11047
• Code: https://github.com/KU-CVLAB/MIDMs

Others for Image Generation

Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation

• Paper: https://arxiv.org/abs/2303.02389
• Code: https://github.com/Ldhlwh/DFMGAN

High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets

• Paper: https://ojs.aaai.org/index.php/AAAI/article/view/25371
• Code: https://github.com/Booooooooooo/CRI

ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories

• Paper: https://arxiv.org/abs/2302.02373
• Code: https://github.com/ckczzj/ShiftDDPMs

Video Generation

StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

• Paper: https://arxiv.org/abs/2301.01081
• Code: https://github.com/FuxiVirtualHuman/styletalk

VIDM: Video Implicit Diffusion Models

• Paper: https://arxiv.org/abs/2212.00235
• Code: https://github.com/MKFMIKU/vidm

[Back-to-Overview]