ECCV2024.md

Awesome-ECCV2024-Low-Level-Vision

A Collection of Papers and Codes for ECCV2024 Low Level Vision

整理汇总下今年ECCV底层视觉(Low-Level Vision)相关的论文和代码，括超分辨率，图像去雨，图像去雾，去模糊，去噪，图像恢复，图像增强，图像去摩尔纹，图像修复，图像质量评价，插帧，图像/视频压缩等任务，具体如下。

欢迎star，fork和PR~

Please feel free to star, fork or PR if helpful~

相关整理(Related Collections)

• Awesome-CVPR2024-ECCV2024-AIGC
• Awesome-CVPR2024/CVPR2021/CVPR2020-Low-Level-Vision
• Awesome-ECCV2020-Low-Level-Vision
• Awesome-Low-Level-Vision-Research-Groups

参考或转载请注明出处

ECCV2024官网：https://eccv.ecva.net/

ECCV接收论文列表：

ECCV完整论文库：https://www.ecva.net/papers.php

开会时间：2024年9月29日-10月4日

论文接收公布时间：2024年

【Contents】

• 1.超分辨率(Super-Resolution)
• 2.图像去雨(Image Deraining)
• 3.图像去雾(Image Dehazing)
• 4.去模糊(Deblurring)
• 5.去噪(Denoising)
• 6.图像恢复(Image Restoration)
• 7.图像增强(Image Enhancement)
• 8.图像修复(Inpainting)
• 9.高动态范围成像(HDR Imaging)
• 10.图像质量评价(Image Quality Assessment)
• 11.插帧(Frame Interpolation)
• 12.视频/图像压缩(Video/Image Compression)
• 13.压缩图像质量增强(Compressed Image Quality Enhancement)
• 14.图像去反光(Image Reflection Removal)
• 15.图像去摩尔纹(Image Demoireing)
• 16.图像上色(Image Colorization)
• 17.图像和谐化(Image Harmonization)
• 18.视频稳相(Video Stabilization)
• 19.图像融合(Image Fusion)
• 20.其他任务(Others)

1.超分辨率(Super-Resolution)

Accelerating Image Super-Resolution Networks with Pixel-Level Classification

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/370_ECCV_2024_paper.php
• Code: https://github.com/3587jjh/PCSR

AdaDiffSR: Adaptive Region-aware Dynamic acceleration Diffusion Model for Real-World Image Super-Resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/1944_ECCV_2024_paper.php
• Code:

Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6903_ECCV_2024_paper.php
• Code:

A New Dataset and Framework for Real-World Blurred Images Super-Resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/4014_ECCV_2024_paper.php
• Code:

Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/7392_ECCV_2024_paper.php
• Code: https://github.com/shangwei5/ST-AVSR

BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical Flow

• Paper: https://www.arxiv.org/abs/2409.15384
• Code: https://github.com/Egkang-Luis/BurstM

Confidence-Based Iterative Generation for Real-World Image Super-Resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/8254_ECCV_2024_paper.php
• Code:

Contourlet Residual for Prompt Learning Enhanced Infrared Image Super-Resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/00391.pdf
• Code: https://github.com/hey-it-s-me/CoRPLE

Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design

• Paper: https://openreview.net/forum?id=B3E8Y8g9GA
• Code: https://github.com/coulsonlee/Dy-DCA-ECCV2024

DCDM: Diffusion-Conditioned-Diffusion Model for Scene Text Image Super-Resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/2357_ECCV_2024_paper.php
• Code: https://github.com/shreygithub/DCDM

Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models

• Paper: https://arxiv.org/abs/2311.15908
• Code: https://github.com/claudiom4sir/StableVSR

Event-Adapted Video Super-Resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/5857_ECCV_2024_paper.php
• Code:

HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/5709_ECCV_2024_paper.php
• Code: https://github.com/XiangZ-0/HiT-SR

KEEP: Kalman-Inspired Feature Propagation for Video Face Super-Resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3752_ECCV_2024_paper.php
• Code: https://github.com/jnjaby/KEEP

Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/8780_ECCV_2024_paper.php
• Code:

Learning Exhaustive Correlation for Spectral Super-Resolution: Where Spatial-Spectral Attention Meets Linear Dependence

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3662_ECCV_2024_paper.php
• Code: https://github.com/nonozhizhiovo/RealArbiSR

Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution

• Paper: https://arxiv.org/abs/2312.00853
• Code: https://github.com/IanYeung/MGLD-VSR

MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/5614_ECCV_2024_paper.php
• Code:

OmniSSR: Zero-shot Omnidirectional Image Super-Resolution using Stable Diffusion Model

• Paper: https://arxiv.org/abs/2404.10312
• Code: https://github.com/LiRunyi2001/OmniSSR

Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks

• Paper: https://arxiv.org/abs/2307.13337
• Code: https://github.com/Cheeun/ODM

Pairwise Distance Distillation for Unsupervised Real-World Image Super-Resolution

• Paper: https://arxiv.org/abs/2407.07302
• Code: https://github.com/Yuehan717/PDD

Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization

• Paper: https://arxiv.org/abs/2308.14469
• Code: https://github.com/yangxy/PASD

RealViformer: Investigating Attention for Real-World Video Super-Resolution

• Paper: https://arxiv.org/abs/2407.13987
• Code: https://github.com/Yuehan717/RealViformer

Rethinking Image Super-Resolution from Training Data Perspectives

• Paper: https://arxiv.org/abs/2409.00768
• Code:

SMFANet: A Lightweight Self-Modulation Feature Aggregation Network for Efficient Image Super-Resolution

• Paper: https://github.com/Zheng-MJ/SMFANet/blob/main/assets/SMFANet.pdf
• Code: https://github.com/Zheng-MJ/SMFANet

Spatially-Variant Degradation Model for Dataset-free Super-resolution

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3655_ECCV_2024_paper.php
• Code: https://github.com/DeepMed-Lab-ECNU/SVDSR

SuperGaussian: Repurposing Video Models for 3D Super Resolution

• Paper: https://arxiv.org/abs/2406.00609
• Code:

UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt

• Paper: https://arxiv.org/abs/2407.13108
• Code: https://github.com/lixinustc/UCIP

XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution

• Paper: https://arxiv.org/abs/2403.05049
• Code: https://github.com/qyp2000/XPSR

You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/4181_ECCV_2024_paper.php
• Code: https://github.com/SamsungLabs/yonos

2.图像去雨(Image Deraining)

Efficient Frequency-Domain Image Deraining with Contrastive Regularization

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/5751_ECCV_2024_paper.php
• Code: https://github.com/deng-ai-lab/FADformer

Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal

• Paper: https://arxiv.org/abs/2407.16957
• Code: https://github.com/jinyeying/RaindropClarity

3.图像去雾(Image Dehazing)

Prompt-Based Test-Time Real Image Dehazing: A Novel Pipeline

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/9815_ECCV_2024_paper.php
• Code: https://github.com/cecret3350/PTTD-Dehazing

Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6072_ECCV_2024_paper.php
• Code:

4.去模糊(Deblurring)

BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting

• Paper: https://arxiv.org/abs/2403.11831
• Code: https://github.com/WU-CVGL/BAD-Gaussians

BeNeRF: Neural Radiance Fields from a Single Blurry Image and Event Stream

• Paper: https://arxiv.org/abs/2407.02174v2
• Code: https://github.com/WU-CVGL/BeNeRF

Blind image deblurring with noise-robust kernel estimation

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3024_ECCV_2024_paper.php
• Code: https://github.com/csleemooo/BD_noise_robust_kernel_estimation

CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring

• Paper: https://arxiv.org/abs/2408.14930
• Code: https://github.com/intelpro/CMTA

Deblur e-NeRF: NeRF from Motion-Blurred Events under High-speed or Low-light Conditions

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/69_ECCV_2024_paper.php
• Code: https://github.com/wengflow/deblur-e-nerf

Deblurring 3D Gaussian Splatting

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/7539_ECCV_2024_paper.php
• Code: https://github.com/benhenryL/Deblurring-3D-Gaussian-Splatting

Domain-adaptive Video Deblurring via Test-time Blurring

• Paper: https://arxiv.org/abs/2407.09059
• Code: https://github.com/Jin-Ting-He/DADeblur

Dynamic Neural Radiance Field From Defocused Monocular Video

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/742_ECCV_2024_paper.php
• Code: https://github.com/xianrui-luo/D2RF

Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion

• Paper: https://arxiv.org/abs/2403.13327
• Code: https://github.com/SpectacularAI/3dgs-deblur

Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6299_ECCV_2024_paper.php
• Code: https://github.com/ChengxuLiu/MISCFilter

Motion Aware Event Representation-driven Image Deblurring

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6299_ECCV_2024_paper.php
• Code: https://github.com/ZhijingS/DA_event_deblur

Rethinking Video Deblurring with Wavelet-Aware Dynamic Transformer and Diffusion Model

• Paper: https://arxiv.org/abs/2408.13459
• Code: https://github.com/Chen-Rao/VD-Diff

Towards Real-world Event-guided Low-light Video Enhancement and Deblurring

• Paper: https://arxiv.org/abs/2408.14916
• Code: https://github.com/intelpro/ELEDNet

UniINR: Event-guided Unified Rolling Shutter Correction, Deblurring, and Interpolation

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/1346_ECCV_2024_paper.php
• Code: https://github.com/yunfanLu/UniINR

5.去噪(Denoising)

Asymmetric Mask Scheme for Self-Supervised Real Image Denoising

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3627_ECCV_2024_paper.php
• Code: https://github.com/lll143653/amsnet

denoiSplit: a method for joint microscopy image splitting and unsupervised denoising

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3482_ECCV_2024_paper.php
• Code:

DualDn: Dual-domain Denoising via Differentiable ISP

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/7547_ECCV_2024_paper.php
• Code: https://github.com/OpenImagingLab/DualDn

EDformer: Transformer-Based Event Denoising Across Varied Noise Levels

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3905_ECCV_2024_paper.php
• Code:

Exploiting Dual-Correlation for Multi-frame Time-of-Flight Denoising

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3302_ECCV_2024_paper.php
• Code:

Region-Aware Sequence-to-Sequence Learning for Hyperspectral Denoising

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/7745_ECCV_2024_paper.php
• Code: https://github.com/gtdong-ustc/multi-frame-tof-denoising

Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers

• Paper: https://arxiv.org/abs/2409.11256
• Code: https://github.com/zfu006/TAP

TTT-MIM: Test-Time Training with Masked Image Modeling for Denoising Distribution Shifts

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/1921_ECCV_2024_paper.php
• Code: https://github.com/MLI-lab/TTT_Denoising

6.图像恢复(Image Restoration)

A Comparative Study of Image Restoration Networks for General Backbone Network Design

• Paper: https://arxiv.org/abs/2310.11881
• Code: https://github.com/Andrew0613/X-Restormer

AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion

• Paper: https://arxiv.org/abs/2310.10123
• Code: https://github.com/jiangyitong/AutoDIR

Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding

• Paper: https://arxiv.org/abs/2407.14816
• Code: https://github.com/jtaoz/GKPILE-Deconvolution

Contribution-based Low-Rank Adaptation with Pre-training Model for Real Image Restoration

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/8074_ECCV_2024_paper.php
• Code:

DAVI: Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems

• Paper: https://arxiv.org/abs/2407.16125
• Code: https://github.com/mlvlab/DAVI

Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems

• Paper: https://arxiv.org/abs/2407.10641
• Code: https://github.com/HJ-harry/DDIP3D

Depth-Aware Blind Image Decomposition for Real-World Adverse Weather Recovery

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/10835_ECCV_2024_paper.php
• Code:

DiffBIR: Toward Blind Image Restoration with Generative Diffusion Prior

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/7690_ECCV_2024_paper.php
• Code: https://github.com/XPixelGroup/DiffBIR

Efficient Cascaded Multiscale Adaptive Network for Image Restoration

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/2840_ECCV_2024_paper.php
• Code:

GAURA: Generalizable Approach for Unified Restoration and Rendering of Arbitrary Views

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/2197_ECCV_2024_paper.php
• Code: https://github.com/Vinayak-VG/GAURA

GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity

• Paper: https://arxiv.org/abs/2407.12273
• Code:

InstructIR: High-Quality Image Restoration Following Human Instructions

• Paper: https://arxiv.org/abs/2401.16468
• Code: https://github.com/mv-lab/InstructIR

Learning Equilibrium Transformation for Gamut Expansion and Color Restoration

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/9030_ECCV_2024_paper.php
• Code: https://github.com/junxiao01/LETNet

MambaIR: A simple baseline for image restoration with state-space model

• Paper: https://arxiv.org/abs/2402.15648
• Code: https://github.com/csguoh/MambaIR

MetaWeather: Few-Shot Weather-Degraded Image Restoration

• Paper: https://arxiv.org/abs/2308.14334
• Code: https://github.com/RangeWING/MetaWeather

MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration

• Paper: https://www.arxiv.org/abs/2407.10833
• Code: https://github.com/renyulin-f/MoE-DiffIR

OneRestore: A Universal Restoration Framework for Composite Degradation

• Paper: https://arxiv.org/abs/2407.04621
• Code: https://github.com/gy65896/OneRestore

Osmosis: RGBD Diffusion Prior for Underwater Image Restoration

• Paper: https://arxiv.org/abs/2403.14837
• Code: https://github.com/osmosis-diffusion/osmosis-diffusion-code

Panel-Specific Degradation Representation for Raw Under-Display Camera Image Restoration

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6479_ECCV_2024_paper.php
• Code: https://github.com/OBAKSA/DREUDC

Quanta Video Restoration

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/5655_ECCV_2024_paper.php
• Code: https://github.com/chennuriprateek/Quanta_Video_Restoration-QUIVER-

RaFE: Generative Radiance Fields Restoration

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/8396_ECCV_2024_paper.php
• Code:

Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6185_ECCV_2024_paper.php
• Code: https://github.com/Dragonisss/RAM

Restoring Images in Adverse Weather Conditions via Histogram Transformer

• Paper: https://arxiv.org/abs/2407.10172
• Code: https://github.com/sunshangquan/Histoformer

Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/2469_ECCV_2024_paper.php
• Code: https://github.com/joshyZhou/FPro

SPIRE: Semantic Prompt-Driven Image Restoration

• Paper: https://arxiv.org/abs/2312.11595
• Code:

Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint

• Paper: https://arxiv.org/abs/2409.15739
• Code: https://github.com/Ephemeral182/ECCV24_T3-DiffWeather

Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models

• Paper: https://arxiv.org/abs/2409.02101
• Code: https://github.com/jiaqixuac/WResVLM

UniProcessor: A Text-induced Unified Low-level Image Processor

• Paper: https://www.arxiv.org/abs/2407.20928
• Code: https://github.com/IntMeGroup/UniProcessor

Unsupervised Variational Translator for Bridging Image Restoration and High-Level Vision Tasks

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/8556_ECCV_2024_paper.php
• Code: https://github.com/IntMeGroup/UniProcessor

When Fast Fourier Transform Meets Transformer for Image Restoration

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6190_ECCV_2024_paper.php
• Code: https://github.com/deng-ai-lab/SFHformer

Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems

• Paper: https://arxiv.org/abs/2407.11288
• Code: https://github.com/ualcalar17/ZAPS

7.图像增强(Image Enhancement)

Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations

• Paper: https://arxiv.org/abs/2407.12511
• Code: https://github.com/ctom2/colie

GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval

• Paper: https://arxiv.org/abs/2407.12431
• Code: https://github.com/LowLevelAI/GLARE

Image-adaptive 3D Lookup Tables for Real-time Image Enhancement with Bilateral Grids

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6517_ECCV_2024_paper.php
• Code: https://github.com/WontaeaeKim/LUTwithBGrid

Joint RGB-Spectral Decomposition Model Guided Image Enhancement in Mobile Photography

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/2012_ECCV_2024_paper.php
• Code: https://github.com/CalayZhou/JDM-HDRNet

Learned Image Enhancement via Color Naming

• Paper: https://arxiv.org/abs/2407.09892
• Code: https://github.com/davidserra9/namedcurves

LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models

• Paper: https://arxiv.org/abs/2407.08939
• Code: https://github.com/JianghaiSCU/LightenDiffusion

LMT-GP: Combined Latent Mean-Teacher and Gaussian Process for Semi-supervised Low-light Image Enhancement

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/11031_ECCV_2024_paper.php
• Code: https://github.com/HFUT-CV/LMT-GP

Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval

• Paper:
• Code: https://github.com/LowLevelAI/GLARE

RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement

• Paper: https://arxiv.org/abs/2404.01889
• Code: https://github.com/Atmyre/RAVE

Taming Lookup Tables for Efficient Image Retouching

• Paper: https://arxiv.org/abs/2403.19238
• Code: https://github.com/Stephen0808/ICELUT

Towards Real-world Event-guided Low-light Video Enhancement and Deblurring

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/1982_ECCV_2024_paper.php
• Code: https://github.com/intelpro/ELEDNet

Unrolled Decomposed Unpaired Learning for Controllable Low-Light Video Enhancement

• Paper: https://arxiv.org/abs/2408.12316
• Code: https://github.com/lingyzhu0101/UDU

Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement

• Paper: https://arxiv.org/abs/2409.01641
• Code: https://github.com/redrock303/ADF-LLIE

8.图像修复(Inpainting)

A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpainting

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/2304_ECCV_2024_paper.php
• Code: https://github.com/segments-ai/latent-diffusion-segmentation

A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting

• Paper: https://arxiv.org/abs/2312.03594
• Code: https://github.com/open-mmlab/PowerPaint

Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation

• Paper: https://arxiv.org/abs/2403.13745
• Code: https://github.com/G-U-N/Be-Your-Outpainter

BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion

• Paper: https://arxiv.org/abs/2403.06976
• Code: https://github.com/TencentARC/BrushNet

GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal

• Paper: https://arxiv.org/abs/2404.13679
• Code: https://github.com/W-Ted/GScream

Improving Text-guided Object Inpainting with Semantic Pre-inpainting

• Paper: https://arxiv.org/abs/2409.08260
• Code: https://github.com/Nnn-s/CaTdiffusion

Leveraging Text Localization for Scene Text Removal via Text-aware Masked Image Modeling

• Paper: https://arxiv.org/abs/2409.13431
• Code: https://github.com/wzx99/TMIM

Single-Mask Inpainting for Voxel-based Neural Radiance Fields

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/7404_ECCV_2024_paper.php
• Code:

Taming Latent Diffusion Model for Neural Radiance Field Inpainting

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/354_ECCV_2024_paper.php
• Code:

9.高动态范围成像(HDR Imaging)

Intrinsic Single-Image HDR Reconstruction

• Paper: https://arxiv.org/abs/2409.13803
• Code:

Optimizing Illuminant Estimation in Dual-Exposure HDR Imaging

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/206_ECCV_2024_paper.php
• Code:

SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging

• Paper: https://arxiv.org/abs/2407.16308
• Code: https://github.com/ltkong218/SAFNet

10.图像质量评价(Image Quality Assessment)

A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment

• Paper: https://arxiv.org/abs/2403.10854
• Code: https://github.com/TianheWu/MLLMs-for-IQA

AID-AppEAL: Automatic Image Dataset and Algorithm for Content Appeal Enhancement and Assessment Labeling

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/2824_ECCV_2024_paper.php
• Code: https://github.com/SherryXTchen/AID-Appeal

Assessing Sample Quality via the Latent Space of Generative Models

• Paper: https://arxiv.org/abs/2407.15171
• Code: https://github.com/cvlab-stonybrook/LS-sample-quality

CrossScore: Towards Multi-View Image Evaluation and Scoring

• Paper: https://arxiv.org/abs/2404.14409
• Code:

Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models

• Paper: https://arxiv.org/abs/2312.08962
• Code: https://github.com/XPixelGroup/DepictQA

DSMix: Distortion-Induced Saliency Map Based Pre-training for No-Reference Image Quality Assessment

• Paper: https://arxiv.org/abs/2407.03886
• Code: https://github.com/I2-Multimedia-Lab/DSMix

Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencoder

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/10006_ECCV_2024_paper.php
• Code: https://github.com/jiajie96/FDD_pytorch

Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/7025_ECCV_2024_paper.php
• Code: https://github.com/real-hjq/MS-SWD

PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/75_ECCV_2024_paper.php
• Code:

Scaling Up Personalized Image Aesthetic Assessment via Task Vector Customization

• Paper: https://arxiv.org/abs/2407.07176
• Code: https://github.com/YeolJ00/Personalized-Aesthetics

Towards Open-ended Visual Quality Comparison

• Paper: https://arxiv.org/abs/2402.16641
• Code: https://github.com/Q-Future/Co-Instruct

11.插帧(Frame Interpolation)

Clearer Frames, Anytime: Resolving Velocity Ambiguity in Video Frame Interpolation

• Paper: https://arxiv.org/abs/2311.08007
• Code: https://github.com/zzh-tech/InterpAny-Clearer

DreamMover: Leveraging the Prior of Diffusion Models for Image Interpolation with Large Motion

• Paper: https://arxiv.org/abs/2409.09605
• Code: https://github.com/leoShen917/DreamMover

Dual-Camera Smoooth Zoom on Mobile Phones

• Paper: https://arxiv.org/abs/2404.04908
• Code: https://github.com/ZcsrenlongZ/ZoomGS

FastPCI: Motion-Structure Guided Fast Point Cloud Frame Interpolation

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/9447_ECCV_2024_paper.php
• Code: https://github.com/genuszty/FastPCI

IAM-VFI : Interpolate Any Motion for Video Frame Interpolation with motion complexity map

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/2398_ECCV_2024_paper.php
• Code: https://github.com/rlghksdbs/IAM-VFI

Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimation

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6123_ECCV_2024_paper.php
• Code: https://github.com/LiuJF1226/Mono-ViFI

TimeLens-XL: Real-time Event-based Video Frame Interpolation with Large Motion

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/11208_ECCV_2024_paper.php
• Code: https://github.com/Mayongrui/TimeLens-XL

12.视频/图像压缩(Video/Image Compression)

A Unified Image Compression Method for Human Perception and Multiple Vision Tasks

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/9009_ECCV_2024_paper.php
• Code:

BaSIC: BayesNet Structure Learning for Computational Scalable Neural Image Compression

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/3640_ECCV_2024_paper.php
• Code: https://github.com/worldlife123/cbench_BaSIC

Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model

• Paper: https://arxiv.org/abs/2407.10632
• Code:

EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation

• Paper: https://arxiv.org/abs/2309.03244
• Code:

Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement

• Paper: https://arxiv.org/abs/2408.02966
• Code:

Free-VSC: Free Semantics from Visual Foundation Models for Unsupervised Video Semantic Compression

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6543_ECCV_2024_paper.php
• Code:

GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting

• Paper: https://arxiv.org/abs/2403.08551
• Code: https://github.com/Xinjie-Q/GaussianImage

HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression

• Paper: https://arxiv.org/abs/2403.14530
• Code: https://github.com/YihangChen-ee/HAC

Image Compression for Machine and Human Vision With Spatial-Frequency Adaptation

• Paper: http://arxiv.org/abs/2407.09853
• Code: https://github.com/qingshi9974/ECCV2024-AdpatICMH

Learned HDR Image Compression for Perceptually Optimal Storage and Display

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/6526_ECCV_2024_paper.php
• Code: https://github.com/cpb68/EPIC-HDR

Learned Rate Control for Frame-Level Adaptive Neural Video Compression via Dynamic Neural Network

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/11394_ECCV_2024_paper.php
• Code:

Long-term Temporal Context Gathering for Neural Video Compression

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/8346_ECCV_2024_paper.php
• Code:

Lossy Image Compression with Foundation Diffusion Models

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/7844_ECCV_2024_paper.php
• Code:

MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/4927_ECCV_2024_paper.php
• Code:

Neural Graphics Texture Compression Supporting Random Acces

• Paper: https://arxiv.org/abs/2407.00021
• Code:

Rate-Distortion-Cognition Controllable Versatile Neural Image Compression

• Paper: https://arxiv.org/abs/2407.11700
• Code:

Region-Adaptive Transform with Segmentation Prior for Image Compression

• Paper: https://arxiv.org/abs/2403.00628
• Code: https://github.com/GityuxiLiu/SegPIC-for-Image-Compression

WeConvene: Learned Image Compression with Wavelet-Domain Convolution and Entropy Model

• Paper: https://arxiv.org/abs/2407.09983
• Code: https://github.com/fengyurenpingsheng/WeConvene

13.压缩图像质量增强(Compressed Image Quality Enhancement)

MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration

• Paper: https://www.arxiv.org/abs/2407.10833
• Code: https://github.com/renyulin-f/MoE-DiffIR

OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removal

• Paper: https://arxiv.org/abs/2408.11480
• Code: https://github.com/QMoQ/OAPT

Online Video Quality Enhancement with Spatial-Temporal Look-up Tables

• Paper: https://arxiv.org/abs/2311.13616
• Code: https://github.com/quzefan/STLVQE

14.图像去反光(Image Reflection Removal)

L-DiffER: Single Image Reflection Removal with Language-based Diffusion Model

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/2988_ECCV_2024_paper.php
• Code:

15.图像去摩尔纹(Image Demoireing)

Image Demoireing in RAW and sRGB Domains

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/929_ECCV_2024_paper.php
• Code: https://github.com/rebeccaeexu/RRID

16.图像上色(Image Colorization)

ColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorization

• Paper: https://arxiv.org/abs/2404.06251
• Code: https://github.com/yyang181/colormnet

17.图像和谐化(Image Harmonization)

Neural Poisson Solver: A Universal and Continuous Framework for Natural Signal Blending

• Paper: https://arxiv.org/abs/2407.08457
• Code:

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering

• Paper: https://arxiv.org/abs/2408.09702
• Code:

18.视频稳相(Video Stabilization)

Eliminating Warping Shakes for Unsupervised Online Video Stitching

• Paper: https://arxiv.org/abs/2403.06378
• Code: https://github.com/nie-lang/StabStitch

19.图像融合(Image Fusion)

LiDAR-Event Stereo Fusion with Hallucinations

• Paper: https://arxiv.org/abs/2408.04633
• Code: https://github.com/bartn8/eventvppstereo

20.其他任务(Others)

Adaptive Compressed Sensing with Diffusion-Based Posterior Sampling

• Paper: https://arxiv.org/abs/2407.08256
• Code: https://github.com/Roninton/ANR

Adaptive Selection of Sampling-Reconstruction in Fourier Compressed Sensing

• Paper: https://arxiv.org/abs/2409.11738
• Code:

A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging

• Paper: https://arxiv.org/abs/2407.21517
• Code: https://github.com/mcao92/QuantizedSCI

Attention Beats Linear for Fast Implicit Neural Representation Generation

• Paper: https://arxiv.org/abs/2407.15355
• Code:

Diff-Reg: Diffusion Model in Doubly Stochastic Matrix Space for Registration Problem

• Paper: https://arxiv.org/abs/2403.19919
• Code: https://github.com/wuqianliang/Diff-Reg

Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation

• Paper: https://arxiv.org/abs/2403.10911
• Code: https://github.com/oyt9306/Decorruptor

Event-Based Motion Magnification

• Paper: https://arxiv.org/abs/2402.11957
• Code: https://github.com/OpenImagingLab/emm

Hierarchical Separable Video Transformer for Snapshot Compressive Imaging

• Paper: https://arxiv.org/abs/2407.11946
• Code: https://github.com/pwangcs/HiSViT

Imaging Interiors: An Implicit Solution to Electromagnetic Inverse Scattering Problems

• Paper: https://arxiv.org/abs/2407.09352
• Code: https://github.com/luo-ziyuan/Imaging-Interiors

Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context

• Paper: https://arxiv.org/abs/2311.17524
• Code:

Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging

• Paper:
• Code: https://github.com/Zongliang-Wu/LADE-DUN

Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics

• Paper: https://arxiv.org/abs/2408.02672
• Code:

Learning to Robustly Reconstruct Low-light Dynamic Scenes from Spike Streams

• Paper: https://arxiv.org/abs/2401.10461
• Code: https://github.com/Acnext/Learning-to-Robustly-Reconstruct-Dynamic-Scenes-from-Low-light-Spike-Streams

LLMCO4MR: LLMs-aided Neural Combinatorial Optimization for Ancient Manuscript Restoration from Fragments with Case Studies on Dunhuang

• Paper: https://www.ecva.net/papers/eccv_2024/papers_ECCV/html/9585_ECCV_2024_paper.php
• Code:

Long-range Turbulence Mitigation: A Large-scale Dataset and A Coarse-to-fine Framework

• Paper: https://arxiv.org/abs/2407.08377
• Code:

Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models

• Paper: https://arxiv.org/abs/2407.10285
• Code: https://github.com/yangqy1110/NC-SDEdit

QueryCDR: Query-based Controllable Distortion Rectification Network for Fisheye Images

• Paper:
• Code: https://github.com/PbGuo/QueryCDR

RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images

• Paper: https://arxiv.org/abs/2408.14802
• Code: https://github.com/cuiziteng/ECCV_RAW_Adapter

Rawformer: Unpaired Raw-to-Raw Translation for Learnable Camera ISPs

• Paper: https://arxiv.org/abs/2404.10700
• Code: https://github.com/gosha20777/rawformer

Real-data-driven 2000 FPS Color Video from Mosaicked Chromatic Spikes

• Paper: https://downloads.ctfassets.net/yreyglvi5sud/3nNNylN8GN96d3Cb8YMAUI/990568aa0bf10b4fb1f8e5e7dba61b22/2024______Yang_ECCV.pdf
• Code:

Revisit Event Generation Model: Self-Supervised Learning of Event-to-Video Reconstruction with Implicit Neural Representations

• Paper: https://arxiv.org/abs/2407.18500
• Code: https://github.com/wzpscott/EvINR

RS-NeRF: Neural Radiance Fields from Rolling Shutter Images

• Paper: https://arxiv.org/abs/2407.10267
• Code: https://github.com/MyNiuuu/RS-NeRF

SAH-SCI: Self-Supervised Adapter for Efficient Hyperspectral Snapshot Compressive Imaging

• Paper:
• Code: https://github.com/lyuxi/SAH-SCI

Self-Supervised Video Desmoking for Laparoscopic Surgery

• Paper: https://arxiv.org/abs/2403.11192
• Code: https://github.com/ZcsrenlongZ/SelfSVD

Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization

• Paper:
• Code: https://github.com/TonyHongtaoWu/SemiVDN

Temporal-Mapping Photography for Event Cameras

• Paper:
• Code: https://github.com/YuHanBaozju/EvTemMap

Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction

• Paper: https://arxiv.org/abs/2407.10636
• Code:

Topology-Preserving Downsampling of Binary Images

• Paper:
• Code: https://github.com/pengchihan/BinaryImageDownsampling

Towards Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularization

• Paper: https://arxiv.org/abs/2312.09988
• Code: https://github.com/YilinLiu97/Untrained-Recon

Towards Robust Event-based Networks for Nighttime via Unpaired Day-to-Night Event Translation

• Paper: https://arxiv.org/abs/2407.10703
• Code: https://github.com/jeongyh98/UDNET

BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering

• Paper: https://arxiv.org/abs/2403.06243
• Code:

持续更新~