图像生成 - arXivDaily 专题

2507.07133 2025-07-11 cs.GR cs.AI cs.LG 70%

Generative Panoramic Image Stitching

Mathieu Tuli, Kaveh Kamali, David B. Lindell

机构 * LG Electronics（LG电子公司）； University of Toronto（多伦多大学）

专题命中图像修复：diffusion(abstract)；inpainting(abstract)；分类 cs.GR

2412.01717 2025-07-09 cs.CV 70%

Driving View Synthesis on Free-form Trajectories with Generative Prior

Zeyu Yang, Zijie Pan, Yuankun Yang, Xiatian Zhu, Li Zhang

机构 * Fudan University（复旦大学）； University of Surrey（Surrey大学）

专题命中图像修复：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

Comments ICCV 2025

2506.02633 2025-06-04 cs.CV 70%

ControlMambaIR: Conditional Controls with State-Space Model for Image Restoration

Cheng Yang, Lijing Liang, Zhixun Su

机构 * DLUT（大连理工大学）

专题命中图像修复：image generation(abstract)；diffusion(abstract)；分类 cs.CV

2504.13622 2025-04-21 eess.IV cs.CV 70%

SupResDiffGAN a new approach for the Super-Resolution task

Dawid Kopeć, Wojciech Kozłowski, Maciej Wizerkaniuk, Dawid Krutul, Jan Kocoń, Maciej Zięba

机构 * WUST, Wybrzeże Stanisława Wyspiańskiego 27, 50-370 Wrocław, Poland（波兰弗罗茨瓦夫大学）

专题命中图像修复：image generation(abstract)；diffusion(abstract)；分类 cs.CV

Comments 25th International Conference on Computational Science

2503.11073 2025-03-17 cs.CV 70%

Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models

Hongyang Wei, Shuaizheng Liu, Chun Yuan, Lei Zhang

专题命中图像修复：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

2501.01235 2025-01-06 cs.CV cs.LG eess.IV 70%

SVFR: A Unified Framework for Generalized Video Face Restoration

Zhiyao Wang, Xu Chen, Chengming Xu, Junwei Zhu, Xiaobin Hu, Jiangning Zhang, Chengjie Wang, Yuqi Liu, Yiyi Zhou, Rongrong Ji

专题命中图像修复：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

2405.18816 2025-01-06 cs.CV cs.LG 70%

Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching

Yasi Zhang, Peiyu Yu, Yaxuan Zhu, Yingshan Chang, Feng Gao, Ying Nian Wu, Oscar Leong

专题命中图像修复：inpainting(abstract)；image synthesis(abstract)；分类 cs.CV

Comments Accepted to NeurIPS 2024

2412.00878 2024-12-09 cs.CV 70%

Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration

Haoze Sun, Wenbo Li, Jiayue Liu, Kaiwen Zhou, Yongqiang Chen, Yong Guo, Yanwei Li, Renjing Pei, Long Peng, Yujiu Yang

专题命中图像修复：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

2405.17673 2024-11-04 cs.CV cs.LG stat.ML 70%

Fast Samplers for Inverse Problems in Iterative Refinement Models

Kushagra Pandey, Ruihan Yang, Stephan Mandt

专题命中图像修复：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

Comments 43 pages, NeurIPS'24 Camera Ready

2410.18666 2024-10-30 cs.CV 70%

DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation

Yuang Ai, Xiaoqiang Zhou, Huaibo Huang, Xiaotian Han, Zhengyu Chen, Quanzeng You, Hongxia Yang

专题命中图像修复：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2024

2407.05259 2024-07-09 eess.IV cs.AI cs.CV cs.LG 70%

Multi-scale Conditional Generative Modeling for Microscopic Image Restoration

Luzhe Huang, Xiongye Xiao, Shixuan Li, Jiawen Sun, Yi Huang, Aydogan Ozcan, Paul Bogdan

专题命中图像修复：image generation(abstract)；diffusion(abstract)；分类 cs.CV

2406.05565 2024-06-11 cs.CV 70%

Medical Vision Generalist: Unifying Medical Imaging Tasks in Context

Sucheng Ren, Xiaoke Huang, Xianhang Li, Junfei Xiao, Jieru Mei, Zeyu Wang, Alan Yuille, Yuyin Zhou

专题命中图像修复：image generation(abstract)；inpainting(abstract)；分类 cs.CV

2311.16518 2024-06-05 cs.CV 70%

SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

Rongyuan Wu, Tao Yang, Lingchen Sun, Zhengqiang Zhang, Shuai Li, Lei Zhang

专题命中图像修复：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Accepted by CVPR2024

2312.10299 2024-05-21 cs.CV cs.AI cs.LG 70%

Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge

Conghan Yue, Zhengwei Peng, Junlong Ma, Shiyan Du, Pengxu Wei, Dongyu Zhang

专题命中图像修复：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

Comments ICML 2024

2404.09732 2024-04-16 cs.CV 70%

Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models

Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön

专题命中图像修复：image generation(abstract)；diffusion(abstract)；分类 cs.CV

Comments CVPRW 2024; Code: https://github.com/Algolzw/daclip-uir

2403.11451 2024-03-19 cs.CV 70%

CasSR: Activating Image Power for Real-World Image Super-Resolution

Haolan Chen, Jinhua Hao, Kai Zhao, Kun Yuan, Ming Sun, Chao Zhou, Wei Hu

专题命中图像修复：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

2403.10585 2024-03-19 eess.IV cs.AI cs.CV cs.LG 70%

Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint

Haoyue Tang, Tian Xie, Aosong Feng, Hanyu Wang, Chenyang Zhang, Yang Bai

专题命中图像修复：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

Comments Accepted and to Appear, AISTATS 2024

2310.16047 2024-03-12 cs.CV cs.LG eess.IV 70%

From Posterior Sampling to Meaningful Diversity in Image Restoration

Noa Cohen, Hila Manor, Yuval Bahat, Tomer Michaeli

专题命中图像修复：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

Comments Accepted for ICLR 2024. Code and examples are available at https://noa-cohen.github.io/MeaningfulDiversityInIR

2403.01124 2024-03-05 cs.CV 70%

Text-guided Explorable Image Super-resolution

Kanchana Vaishnavi Gandikota, Paramanand Chandramouli

专题命中图像修复：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments CVPR 2024

2311.16512 2023-12-22 cs.CV cs.AI 70%

CoSeR: Bridging Image and Language for Cognitive Super-Resolution

Haoze Sun, Wenbo Li, Jianzhuang Liu, Haoyu Chen, Renjing Pei, Xueyi Zou, Youliang Yan, Yujiu Yang

专题命中图像修复：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Project page: https://coser-main.github.io ; GitHub repository: https://github.com/VINHYU/CoSeR

2311.02358 2023-12-22 eess.IV cs.CV 70%

Domain Transfer in Latent Space (DTLS) Wins on Image Super-Resolution -- a Non-Denoising Model

Chun-Chuen Hui, Wan-Chi Siu, Ngai-Fong Law

专题命中图像修复：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

2309.15533 2023-11-07 cs.CV cs.LG eess.IV stat.ML 70%

Uncertainty Quantification via Neural Posterior Principal Components

Elias Nehme, Omer Yair, Tomer Michaeli

专题命中图像修复：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

Comments NeurIPS 2023 Camera Ready, interactive examples at https://eliasnehme.github.io/NPPC/

2302.06733 2023-06-23 cs.CV 70%

Robust Unsupervised StyleGAN Image Restoration

Yohan Poirier-Ginter, Jean-François Lalonde

专题命中图像修复：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

Comments 8 pages, accepted at CVPR 2023

2302.05872 2023-05-29 cs.CV cs.LG stat.ML 70%

I$^2$SB: Image-to-Image Schrödinger Bridge

Guan-Horng Liu, Arash Vahdat, De-An Huang, Evangelos A. Theodorou, Weili Nie, Anima Anandkumar

专题命中图像修复：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

Comments ICML camera ready (high-resolution figures)

2305.01165 2023-05-03 eess.IV cs.CV physics.optics 70%

Self-similarity-based super-resolution of photoacoustic angiography from hand-drawn doodles

Yuanzheng Ma, Wangting Zhou, Rui Ma, Sihua Yang, Yansong Tang, Xun Guan

专题命中图像修复：image generation(abstract)；diffusion(abstract)；分类 cs.CV

Comments 12 pages, 6 figures, journal

2104.07636 2021-07-01 eess.IV cs.CV cs.LG 70%

Image Super-Resolution via Iterative Refinement

Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David J. Fleet, Mohammad Norouzi

专题命中图像修复：image generation(abstract)；diffusion(abstract)；分类 cs.CV

2011.11309 2020-11-25 cs.CV 70%

Legacy Photo Editing with Learned Noise Prior

Zhao Yuzhi, Po Lai-Man, Wang Xuehui, Liu Kangcheng, Zhang Yujia, Yu Wing-Yin, Xian Pengfei, Xiong Jingjing

专题命中图像修复：image editing(abstract)；inpainting(abstract)；分类 cs.CV

Comments accepted by IEEE WACV 2021, 2nd round submission

1711.10925 2020-05-19 cs.CV stat.ML 70%

Deep Image Prior

Dmitry Ulyanov, Andrea Vedaldi, Victor Lempitsky

专题命中图像修复：image generation(abstract)；inpainting(abstract)；分类 cs.CV

1912.07116 2020-04-01 cs.CV 70%

Image Processing Using Multi-Code GAN Prior

Jinjin Gu, Yujun Shen, Bolei Zhou

专题命中图像修复：inpainting(abstract)；image synthesis(abstract)；分类 cs.CV

Comments CVPR2020 camera-ready

1911.00689 2019-11-05 cs.CV cs.LG eess.IV 70%

Pixel-wise Conditioning of Generative Adversarial Networks

Cyprien Ruffino, Romain Hérault, Eric Laloy, Gilles Gasso

专题命中图像修复：image generation(abstract)；inpainting(abstract)；分类 cs.CV

1. 图像修复 1784 篇

Generative Panoramic Image Stitching

Driving View Synthesis on Free-form Trajectories with Generative Prior

ControlMambaIR: Conditional Controls with State-Space Model for Image Restoration

SupResDiffGAN a new approach for the Super-Resolution task

Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models

SVFR: A Unified Framework for Generalized Video Face Restoration

Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching

Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration

Fast Samplers for Inverse Problems in Iterative Refinement Models

DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation

Multi-scale Conditional Generative Modeling for Microscopic Image Restoration

Medical Vision Generalist: Unifying Medical Imaging Tasks in Context

SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge

Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models

CasSR: Activating Image Power for Real-World Image Super-Resolution

Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint

From Posterior Sampling to Meaningful Diversity in Image Restoration

Text-guided Explorable Image Super-resolution

CoSeR: Bridging Image and Language for Cognitive Super-Resolution

Domain Transfer in Latent Space (DTLS) Wins on Image Super-Resolution -- a Non-Denoising Model

Uncertainty Quantification via Neural Posterior Principal Components

Robust Unsupervised StyleGAN Image Restoration

I$^2$SB: Image-to-Image Schrödinger Bridge

Self-similarity-based super-resolution of photoacoustic angiography from hand-drawn doodles

Image Super-Resolution via Iterative Refinement

Legacy Photo Editing with Learned Noise Prior

Deep Image Prior

Image Processing Using Multi-Code GAN Prior

Pixel-wise Conditioning of Generative Adversarial Networks