图像生成

Ink removal from histopathology whole slide images by combining classification, detection and image generation models

Sharib Ali, Nasullah Khalid Alham, Clare Verrill, Jens Rittscher

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

Comments Accepted paper at IEEE International Symposium on Biomedical Imaging (ISBI) 2019, Venice, Italy

TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation

Zihan Ding, Xiao-Yang Liu, Miao Yin, Linghe Kong

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

Deep End-to-end Fingerprint Denoising and Inpainting

Youness Mansar

专题命中 图像修复 ：inpainting(title)；分类 cs.CV

Comments Winning solution to the Chalearn LAP In-painting Competition Track 3 / Accepted in the 2018 Chalearn Looking at People Satellite Workshop ECCV

Inpainting of long audio segments with similarity graphs

Nathanael Perraudin, Nicki Holighaus, Piotr Majdak, Peter Balazs

专题命中 图像修复 ：inpainting(title)；分类 cs.MM

Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks

Weiyue Wang, Qiangui Huang, Suya You, Chao Yang, Ulrich Neumann

专题命中 图像修复 ：inpainting(title)；分类 cs.CV

MESA: A Training-Free Multi-Exemplar Deep Framework for Restoring Ancient Inscription Textures

MESA：一种无需训练的多示例深度框架，用于恢复古代铭文纹理

Vasileios Toulatzis, Sofia Theodoridou, Ioannis Fudos

机构 * Department of Computer Science and Engineering（计算机科学与工程系） ； University of Ioannina（伊奥安纳大学） ； Inria Paris-Rocquencourt（巴黎-罗克琴堡研究所） ； Rajiv Gandhi University（拉朱·甘地大学） ； Tsinghua University（清华大学） ； Palmer Research Laboratories（帕勒尔研究实验室） 纠错

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

AI总结 MESA通过多示例和风格感知方法，利用保存良好的铭文示例指导损坏文本的重建，通过编码VGG19卷积特征为Gram矩阵捕捉纹理和笔画结构，并结合OCR估计的字符宽度优化滤波器尺度，实现高效修复。

PixelBoost: Leveraging Brownian Motion for Realistic-Image Super-Resolution

Aradhana Mishra, Bumshik Lee

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

PanoGen++: Domain-Adapted Text-Guided Panoramic Environment Generation for Vision-and-Language Navigation

Sen Wang, Dongliang Zhou, Liang Xie, Chao Xu, Ye Yan, Erwei Yin

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

Comments This paper was accepted by Neural Networks

Generative Powers of Ten

Xiaojuan Wang, Janne Kontkanen, Brian Curless, Steve Seitz, Ira Kemelmacher, Ben Mildenhall, Pratul Srinivasan, Dor Verbin, Aleksander Holynski

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

Comments Project page: https://powers-of-10.github.io/

Neural Knitworks: Patched Neural Implicit Representation Networks

Mikolaj Czerkawski, Javier Cardona, Robert Atkinson, Craig Michie, Ivan Andonovic, Carmine Clemente, Christos Tachtatzis

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

Comments Published in Pattern Recognition

Journal ref Volume 151, 2024, Page 110378

Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasets

Ji Xia, Yizi Zhang, Shuqi Wang, Genevera I. Allen, Liam Paninski, Cole Lincoln Hurwitz, Kenneth D. Miller

专题命中 图像修复 ：inpainting(title)

Voice-ENHANCE: Speech Restoration using a Diffusion-based Voice Conversion Framework

Kyungguen Byun, Jason Filos, Erik Visser, Sunkuk Moon

机构 * Qualcomm Technologies Inc.（高通技术公司） 纠错

专题命中 图像修复 ：diffusion(title)

Comments 5 pages, 3 figures, Accepted to INTERSPEECH 2025

Cross-modal Medical Image Generation Based on Pyramid Convolutional Attention Network

Fuyou Mao, Lixin Lin, Ming Jiang, Dong Dai, Chao Yang, Hao Zhang, Yan Tang

专题命中 图像修复 ：image generation(title)

Comments 18 pages, 6 figures, Machine Vision and Applications

CSR-dMRI: Continuous Super-Resolution of Diffusion MRI with Anatomical Structure-assisted Implicit Neural Representation Learning

Ruoyou Wu, Jian Cheng, Cheng Li, Juan Zou, Jing Yang, Wenxin Fan, Yong Liang, Shanshan Wang

专题命中 图像修复 ：diffusion(title)

Comments 10 pages

Inpainting Galaxy Counts onto N-Body Simulations over Multiple Cosmologies and Astrophysics

Antoine Bourdin, Ronan Legin, Matthew Ho, Alexandre Adam, Yashar Hezaveh, Laurence Perreault-Levasseur

专题命中 图像修复 ：inpainting(title)

Comments 7+4 pages, 3+1 figures, accepted at the ICML 2024 Workshop AI4Science

Joint Data Inpainting and Graph Learning via Unrolled Neural Networks

Subbareddy Batreddy, Pushkal Mishra, Yaswanth Kakarla, Aditya Siripuram

专题命中 图像修复 ：inpainting(title)

Network Inpainting via Optimal Transport

Enrico Facca, Jan Martin Nordbotten, Erik Andreas Hanson

专题命中 图像修复 ：inpainting(title)

Inpainting Computational Fluid Dynamics with Deep Learning

Dule Shu, Wilson Zhen, Zijie Li, Amir Barati Farimani

专题命中 图像修复 ：inpainting(title)

Comments 20 pages, 9 figures

Sparse InSAR Data 3D Inpainting for Ground Deformation Detection Along the Rail Corridor

Odysseas Pappas, Juliet Biggs, David Bull, Alin Achim, Nantheera Anantrasirichai

专题命中 图像修复 ：inpainting(title)

Comments in submission to ICIP 2022

Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining

Oriel Frigo, Rémy Brossard, David Dehaene

专题命中 图像修复 ：inpainting(title)

Comments 13 pages, 4 figures

Inpainting CMB maps using Partial Convolutional Neural Networks

Gabriele Montefalcone, Maximilian H. Abitbol, Darsh Kodwani, R. D. P. Grumitt

专题命中 图像修复 ：inpainting(title)

Comments 17 pages, 6 figures, 1 table

Journal ref JCAP03(2021)055

Image Generation With Neural Cellular Automatas

Mingxiang Chen, Zhecheng Wang

专题命中 图像修复 ：image generation(title)

Sound field reconstruction in rooms: inpainting meets super-resolution

Francesc Lluís, Pablo Martínez-Nuevo, Martin Bo Møller, Sven Ewan Shepstone

专题命中 图像修复 ：inpainting(title)

Comments Code: https://github.com/francesclluis/sound-field-neural-network

Journal ref The Journal of the Acoustical Society of America 148, 649 (2020)

Non-local tensor completion for multitemporal remotely sensed images inpainting

Teng-Yu Ji, Naoto Yokoya, Xiao Xiang Zhu, Ting-Zhu Huang

专题命中 图像修复 ：inpainting(title)

Coupled variational problems of linear growth related to the denoising and inpainting of images

Jan Mueller

专题命中 图像修复 ：inpainting(title)

Journal ref Journal of Mathematical Sciences, August 2017, Volume 224, Issue 5, pp 709-734

A higher order TV-type variational problem related to the denoising and inpainting of images

Martin Fuchs, Jan Mueller

专题命中 图像修复 ：inpainting(title)

Journal ref Nonlinear Analysis: Theory, Methods & Applications Volume 154, May 2017, Pages 122-147

MagnifiQ: Patch-aware Text Guided Progressive Upscaling for High-Resolution Image Restoration

MagnifiQ：面向高分辨率图像修复的感知补丁文本引导渐进式上采样方法

Mahesh Reddy, Yashesh Savani, Antoine Mercier, Hong Cai, Fatih Porikli, Guillaume Berger

机构 * Qualcomm AI Research（高通人工智能研究中心） 纠错

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

AI总结 MagnifiQ是一种跨分辨率渐进式上采样的图像修复框架，替换扩散模型自注意力层为线性计算卷积，采用补丁文本提示，在4K图像修复中性能优于现有方法，实现速度与质量的实用权衡。

Comments Camera-ready version (ECCV workshop - LoViF'26)

Global Attention-Fused Image Cropping with Attention-Guided and Global-Aligned Crop Evaluator

融合全局注意力的图像裁剪方法：基于注意力引导与全局对齐的裁剪评估器

Haotian Yang, Zhile Yang, Kin-Man Lam, Patrick Le Callet, Xin Sun

机构 * Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院） ； Shenzhen University of Advanced Technology（深圳理工大学） ； Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院） ； The Hong Kong Polytechnic University（香港理工大学） ； Nantes Université（南特大学） ； Ecole Centrale Nantes（南特中央理工学院） ； CAPACITES SAS（CAPACITES SAS公司） ； CNRS（法国国家科学研究中心） ； LS2N, UMR 6004（LS2N实验室（UMR 6004）） 纠错

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

AI总结 该研究提出GAFIC图像裁剪方法，通过AGFF与GACE模块结合多尺度排序损失，在GAIC、CPC数据集上性能优于现有方法，适用于需保证像素完整性与高效批量处理的场景。

Comments The source code is available at https://github.com/AIVRC/GAFIC.git

InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem

InverseCrafter：作为潜在域逆问题的高效视频重新捕捉

Yeobin Hong, Suhyeon Lee, Hyungjin Chung, Jong Chul Ye

机构 * Graduate School of AI, KAIST, South Korea（韩国釜山国立大学人工智能研究生院） ； EverEx, South Korea（韩国EverEx公司） ； Korea University, South Korea（韩国国立庆熙大学） 纠错

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

AI总结 提出InverseCrafter框架，将新视角视频生成转化为潜在空间基于图像修复的逆问题，通过轻量级潜在掩码编码器建立算子等价，无需标注4D训练数据，实现高效合成与编辑。

Comments ECCV 2026

NullFlow: One-Step Generative Reconstruction

NullFlow: 一步生成式重建

Xiao Shi, Edward P. Chandler, Chicago Y. Park, Shirin Shoushtari, Ulugbek S. Kamilov

机构 * University of Wisconsin–Madison（威斯康星大学麦迪逊分校） ； Washington University in St. Louis（圣路易斯华盛顿大学） 纠错

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

AI总结 提出NullFlow框架，通过将生成流限制在测量一致子空间实现一步图像重建，无需数据保真校正，学习平均速度避免逐步积分，在图像修复中达到SOTA性能且仅需一次网络评估。

Comments 9 pages, 3 figures. Xiao Shi and Edward P. Chandler contributed equally