Awesome

Awesome-NeurIPS2023-Low-Level-Vision

A Collection of Papers and Codes in NeurIPS2023 related to Low-Level Vision

Related collections for low-level vision

• Awesome-NeurIPS2021-Low-Level-Vision
• Awesome-NeurIPS2022-Low-Level-Vision
• Awesome-ICCV2023/2021-Low-Level-Vision
• Awesome-CVPR2023/2022-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

• Super Resolution

• Denoising

• Deblurring

• Deraining

• Image Enhancement

• Image Matting

• Image Compression

• Image Quality Assessment

• Image Editing

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

  • Video Generation

• Others

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

Image Restoration

Training Your Image Restoration Network Better with Random Weight Network as Optimization Function

• Paper: https://openreview.net/forum?id=uv3ge0goPa

PromptIR: Prompting for All-in-One Blind Image Restoration

• Paper: https://arxiv.org/abs/2306.13090
• Code: https://github.com/va1shn9v/PromptIR
• Tags: All-in-One, Prompt

PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance

• Paper: https://arxiv.org/abs/2309.10810
• Code: https://github.com/pq-yang/PGDiff
• Tags: Diffusion

PromptRestorer: A Prompting Image Restoration Method with Degradation Perception

• Paper: https://openreview.net/forum?id=nIaNgaQvsV
• Tags: Prompt

Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems

• Paper: https://arxiv.org/abs/2306.03466

A Unified Conditional Framework for Diffusion-based Image Restoration

• Paper: https://arxiv.org/abs/2305.20049
• Code: https://github.com/zhangyi-3/UCDIR

Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration

• Paper: https://arxiv.org/abs/2306.02342
• Tags: Real

Video Restoration

Video Dynamics Prior: An Internal Learning Approach for Robust Video Enhancements

• Paper: https://arxiv.org/abs/2312.07835

[Back-to-Overview]

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

Super Resolution

QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution

• Paper: https://openreview.net/forum?id=3gamyee9Yh
• Code: https://github.com/htqin/QuantSR
• Tags: Efficient

Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction

• Paper: https://arxiv.org/abs/2310.19011
• Code: https://github.com/dengzeshuai/srtta

AND: Adversarial Neural Degradation for Learning Blind Image Super-Resolution

• Paper: https://openreview.net/forum?id=s8QsYV1VZ2
• Tag: Blind

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting

• Paper: https://arxiv.org/abs/2307.12348
• Code: https://github.com/zsyOAOA/ResShift
• Tags: Diffusion

Learning Re-sampling Methods with Parameter Attribution for Image Super-resolution

• Paper: https://openreview.net/forum?id=f7wFwPJwBe

Real-World Image Super-Resolution as Multi-Task Learning

• Paper: https://openreview.net/forum?id=8SCz56sUGP
• Tags: Real

Spatio-Angular Convolutions for Super-resolution in Diffusion MRI

• Paper: https://arxiv.org/abs/2306.00854

[Back-to-Overview]

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

Denoising

Normalization-Equivariant Neural Networks with Application to Image Denoising

• Paper: https://arxiv.org/abs/2306.05037
• Code: https://github.com/sherbret/normalization_equivariant_nn/

PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising

• Paper: https://arxiv.org/abs/2310.10088
• Code: https://github.com/HyemiEsme/PUCA

Unsupervised Image Denoising with Score Function

• Paper: https://arxiv.org/abs/2304.08384

[Back-to-Overview]

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

Deblurring

Hierarchical Integration Diffusion Model for Realistic Image Deblurring

• Paper: https://arxiv.org/abs/2305.12966
• Code: https://github.com/zhengchen1999/HI-Diff

Enhancing Motion Deblurring in High-Speed Scenes with Spike Streams

• Paper: https://openreview.net/forum?id=cAyLnMxiTl

[Back-to-Overview]

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

Deraining

Networks are Slacking Off: Understanding Generalization Problem in Image Deraining

• Paper: https://arxiv.org/abs/2305.15134

[Back-to-Overview]

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

Image Enhancement

Transition-constant Normalization for Image Enhancement

• Paper: https://openreview.net/forum?id=GEWzHeHpLr

Global Structure-Aware Diffusion Process for Low-Light Image Enhancement

• Paper: https://arxiv.org/abs/2310.17577
• Code: https://github.com/jinnh/GSAD

[Back-to-Overview]

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

Image Matting

BiMatting: Efficient Video Matting via Binarization

• Paper: https://openreview.net/forum?id=YbYQ0JEQ80
• Code: https://github.com/htqin/BiMatting

[Back-to-Overview]

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

Image Compression

Lossy Image Compression with Conditional Diffusion Models

• Paper: https://arxiv.org/abs/2209.06950
• Code: https://github.com/buggyyang/CDC_compression

Idempotent Learned Image Compression with Right-Inverse

• Paper: https://openreview.net/forum?id=35dOU92OJM

Towards Efficient Image Compression Without Autoregressive Models

• Paper: https://openreview.net/forum?id=1ihGy9vAIg

Neural Image Compression: Generalization, Robustness, and Spectral Biases

• Paper: https://arxiv.org/abs/2307.08657
• Code: https://github.com/klieberman/ood_nic

Video Compression

On the Choice of Perception Loss Function for Learned Video Compression

• Paper: https://arxiv.org/abs/2305.19301

HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation

• Paper: https://arxiv.org/abs/2306.09818
• Code: https://github.com/hmkx/HiNeRV

[Back-to-Overview]

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

Image Quality Assessment

Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks

• Paper: https://arxiv.org/abs/2309.13609
• Code: https://github.com/GZHU-DVL/AttackVQA

Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment

• Paper: https://arxiv.org/abs/2305.10983
• Code: https://github.com/TianheWu/Assessor360

[Back-to-Overview]

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

Image Editing

Video Editing

[Back-to-Overview]

<a name=ImageGeneration></a>

Image Generation/Synthesis / Image-to-Image Translation

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

Image-to-Image / Image Guided

Others for image generation

<a name="VideoGeneration"></a>

Video Generation

[Back-to-Overview]

<a name="Others"></a>

Others

Talking Head Generation

Virtual Try-on

Handwriting/Font Generation

Layout Generation