图像生成 - arXivDaily 专题

2503.00605 2025-03-18 cs.GR cs.CV 62%

GenVDM: Generating Vector Displacement Maps From a Single Image

Yuezhi Yang, Qimin Chen, Vladimir G. Kim, Siddhartha Chaudhuri, Qixing Huang, Zhiqin Chen

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

Comments accepted to CVPR2025

2412.06592 2024-12-10 cs.CV cs.GR 62%

PrEditor3D: Fast and Precise 3D Shape Editing

Ziya Erkoç, Can Gümeli, Chaoyang Wang, Matthias Nießner, Angela Dai, Peter Wonka, Hsin-Ying Lee, Peiye Zhuang

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

Comments Project Page: https://ziyaerkoc.com/preditor3d/ Video: https://www.youtube.com/watch?v=Ty2xXaEuewI

2410.21310 2024-10-30 cs.CV cs.GR 62%

ArCSEM: Artistic Colorization of SEM Images via Gaussian Splatting

Takuma Nishimura, Andreea Dogaru, Martin Oeggerli, Bernhard Egger

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

Comments presented and published at AI for Visual Arts Workshop and Challenges (AI4VA) in conjunction with European Conference on Computer Vision (ECCV) 2024, Milano, Italy

2406.13393 2024-09-05 cs.CV cs.GR 62%

Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images

Haruo Fujiwara, Yusuke Mukuta, Tatsuya Harada

专题命中图像编辑：diffusion(abstract)；分类 cs.CV、cs.GR

Comments 16 pages, 9 figures

2311.16037 2024-07-25 cs.CV cs.GR 62%

GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions

Junjie Wang, Jiemin Fang, Xiaopeng Zhang, Lingxi Xie, Qi Tian

专题命中图像编辑：diffusion(abstract)；分类 cs.CV、cs.GR

Comments CVPR 2024, Project page: https://GaussianEditor.github.io

2312.14383 2023-12-25 cs.MM cs.CV eess.IV 62%

Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal

Yicheng Leng, Chaowei Fang, Gen Li, Yixiang Fang, Guanbin Li

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.MM

Comments Accepted by AAAI2024

2311.16127 2023-11-29 cs.CV cs.GR 62%

SeamlessNeRF: Stitching Part NeRFs with Gradient Propagation

Bingchen Gong, Yuehao Wang, Xiaoguang Han, Qi Dou

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

Comments To appear in SIGGRAPH Asia 2023. Project website is accessible at https://sites.google.com/view/seamlessnerf

2009.05158 2023-06-27 cs.CV cs.CR cs.LG cs.MM 62%

OCR Graph Features for Manipulation Detection in Documents

Hailey Joren, Otkrist Gupta, Dan Raviv

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.MM

2211.13226 2023-06-09 cs.CV cs.GR 62%

ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field

Yuan Li, Zhi-Hao Lin, David Forsyth, Jia-Bin Huang, Shenlong Wang

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

Comments project page: https://climatenerf.github.io/

2303.12789 2023-06-02 cs.CV cs.GR 62%

Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions

Ayaan Haque, Matthew Tancik, Alexei A. Efros, Aleksander Holynski, Angjoo Kanazawa

专题命中图像编辑：diffusion(abstract)；分类 cs.CV、cs.GR

Comments Project website: https://instruct-nerf2nerf.github.io; v1. Revisions to related work and discussion

2304.14403 2023-04-28 cs.CV cs.GR cs.LG 62%

Make It So: Steering StyleGAN for Any Image Inversion and Editing

Anand Bhattad, Viraj Shah, Derek Hoiem, D. A. Forsyth

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

Comments project: https://anandbhattad.github.io/makeitso/

2209.00349 2023-01-03 cs.CV cs.GR 62%

FLAME: Free-form Language-based Motion Synthesis & Editing

Jihoon Kim, Jiseob Kim, Sungjoon Choi

专题命中图像编辑：diffusion(abstract)；分类 cs.CV、cs.GR

Comments AAAI 2023

2205.12639 2022-12-15 cs.CV cs.GR 62%

TreEnhance: A Tree Search Method For Low-Light Image Enhancement

Marco Cotogni, Claudio Cusano

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

Comments Accepted in Pattern Recognition

2108.12947 2022-05-26 eess.IV cs.CV cs.LG cs.MM 62%

Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization

Myung-Joon Kwon, Seung-Hun Nam, In-Jae Yu, Heung-Kyu Lee, Changick Kim

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.MM

Comments The version of record of this article, published in the International Journal of Computer Vision (IJCV), is available online at Publisher's website: https://link.springer.com/article/10.1007/s11263-022-01617-5 ; Code is available at: https://github.com/mjkwon2021/CAT-Net

Journal ref International Journal of Computer Vision (IJCV), 2022

2104.07661 2022-05-11 cs.CV cs.GR 62%

E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion

Tianyi Wei, Dongdong Chen, Wenbo Zhou, Jing Liao, Weiming Zhang, Lu Yuan, Gang Hua, Nenghai Yu

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

Comments To Appear at TIP 2022

2107.02434 2022-02-21 cs.CV cs.MM 62%

Self-Adversarial Training incorporating Forgery Attention for Image Forgery Localization

Long Zhuo, Shunquan Tan, Bin Li, Jiwu Huang

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.MM

Comments accepted by TIFS

2201.08361 2022-01-24 cs.CV cs.GR cs.LG 62%

Stitch it in Time: GAN-Based Facial Editing of Real Videos

Rotem Tzaban, Ron Mokady, Rinon Gal, Amit H. Bermano, Daniel Cohen-Or

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

Comments Project website: https://stitch-time.github.io/

2012.09036 2021-10-19 cs.CV cs.GR 62%

Improved StyleGAN Embedding: Where are the Good Latents?

Peihao Zhu, Rameen Abdal, Yipeng Qin, John Femiani, Peter Wonka

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

2109.01980 2021-09-07 cs.CV cs.GR cs.LG 62%

Deep Saliency Prior for Reducing Visual Distraction

Kfir Aberman, Junfeng He, Yossi Gandelsman, Inbar Mosseri, David E. Jacobs, Kai Kohlhoff, Yael Pritch, Michael Rubinstein

专题命中图像编辑：inpainting(abstract)；分类 cs.CV、cs.GR

Comments https://deep-saliency-prior.github.io/

2107.11186 2021-07-26 cs.CV cs.GR cs.LG 62%

LARGE: Latent-Based Regression through GAN Semantics

Yotam Nitzan, Rinon Gal, Ofir Brenner, Daniel Cohen-Or

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

Comments Code at https://github.com/YotamNitzan/LARGE

2010.01424 2020-10-06 cs.CV cs.AI cs.MM 62%

MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network

Yi Wei, Zhe Gan, Wenbo Li, Siwei Lyu, Ming-Ching Chang, Lei Zhang, Jianfeng Gao, Pengchuan Zhang

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.MM

Comments published at ACCV2020

1907.03118 2019-07-09 cs.CV cs.GR eess.IV 62%

Fast Universal Style Transfer for Artistic and Photorealistic Rendering

Jie An, Haoyi Xiong, Jiebo Luo, Jun Huan, Jinwen Ma

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.GR

1706.06651 2017-06-22 cs.MM cs.CV 62%

Passive Classification of Source Printer using Text-line-level Geometric Distortion Signatures from Scanned Images of Printed Documents

Hardik Jain, Gaurav Gupta, Sharad Joshi, Nitin Khanna

专题命中图像编辑：image editing(abstract)；分类 cs.CV、cs.MM

Comments 20 pages

1612.04337 2016-12-14 cs.CV cs.GR cs.LG 62%

Fast Patch-based Style Transfer of Arbitrary Style

Tian Qi Chen, Mark Schmidt

专题命中图像编辑：image synthesis(abstract)；分类 cs.CV、cs.GR

2510.03906 2026-01-27 cs.CV 61%

From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation Performance

从滤波器到视觉语言模型：通过目标检测和分割性能评估去雾方法

Ardalan Aryashad, Parsa Razmara, Amin Mahjoub, Seyedarmin Azizi, Mahdi Salmani, Arad Firouzkouhi

机构 * University of Southern California（南加州大学）

专题命中图像编辑：image editing(abstract)；分类 cs.CV；diffusion(comments)

AI总结本文通过目标检测和分割性能评估，探讨了去雾方法在真实与合成环境中的有效性，揭示了视觉语言模型在恶劣天气下的应用潜力。

Comments Accepted at WACV 2026 Proceedings (Oral), 5th Workshop on Image, Video, and Audio Quality Assessment in Computer Vision, with a focus on VLM and Diffusion Models

2608.12876 2026-08-14 cs.CV cs.AI 新提交 57%

SPARED: Reasoning-Based AI-Generated Image Detection via Adversarially Edited Data

SPARED：基于推理的AI生成图像检测方法，采用对抗编辑数据

Yicheng Bao, Xiahui Guo, Xuhong Wang, Xin Tan

专题命中图像编辑：diffusion(abstract)；分类 cs.CV

AI总结本研究提出对抗强化学习框架SPARED，通过扩散图像编辑器与推理型MLLM的交替博弈，训练出能抗捷径、泛化能力强的AI生成图像检测器，在三个外部基准上性能单调提升。

2608.09057 2026-08-14 cs.CV 版本更新 57%

Model the Edit, Not the Image: Visual Autoregressive Editing from a Source-Centric Perspective

建模编辑，而非图像：以源为中心视角的视觉自回归编辑

Hongyi Fang, Chuwen Xie, Benjia Zhou, Yu-Xuan Qiu, Chenggong Hu, Zhibin Wang, Chao Chen, Jianbin Qin, Rui Mao

专题命中图像编辑：image editing(abstract)；分类 cs.CV

AI总结该研究针对视觉自回归模型（VARs）编辑的现有不足，提出以源为中心视角的EditMod方法，实现了高保真度与强文本对齐的1K图像端到端编辑，速度达1.57秒/张A100 GPU。

2608.10798 2026-08-13 cs.CV cs.AI cs.LG 版本更新 57%

Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization

超越固定亮度：迈向全色与正色图像上色

Swarnim Maheshwari, Syed Imam Ali, Vineeth N. Balasubramanian

专题命中图像编辑：image editing(abstract)；分类 cs.CV

AI总结该研究针对固定亮度图像上色系统在正色摄影输入下不可靠的问题，提出基于基础图像编辑模型的亮度无关框架，结合混合灰度目标训练，提升了正色输入上色的鲁棒性并减少色彩伪影。

Comments Accepted at ECCV 2026

2512.07826 2026-08-13 cs.CV 版本更新 57%

OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing

OpenVE-3M: 一种大规模高质量的指令引导视频编辑数据集

Haoyang He, Jie Wang, Jiangning Zhang, Zhucun Xue, Xingyuan Bu, Qiangpeng Yang, Shilei Wen, Lei Xie

机构 * Zhejiang University（浙江大学）； ByteDance（字节跳动）

专题命中图像编辑：image editing(abstract)；分类 cs.CV

AI总结 OpenVE-3M是一个大规模高质量的指令引导视频编辑数据集，包含多种编辑类型，通过精心设计的数据管道生成，并展示了高效的5B模型在基准测试中的卓越性能。

Comments Accepted by ECCV'26. Project page: https://lewandofskee.github.io/projects/OpenVE

2608.10870 2026-08-12 cs.CV 新提交 57%

NullEdit: Stealthy Image Protection via VLM Condition Redirection

NullEdit：通过视觉语言模型条件重定向实现隐秘图像保护

Weiyao Huang, Liqin Wang, Ziqi Sheng, Wei Lu

专题命中图像编辑：diffusion(abstract)；分类 cs.CV

AI总结 NullEdit针对VLM表示进行重定向，可隐秘抑制图像编辑且保留源内容，在基准模型上平均降低EditReward IF分数0.813，实现了高效的图像保护。

Comments 9 pages, 6 figures, 3 tables

1. 图像编辑 1258 篇

GenVDM: Generating Vector Displacement Maps From a Single Image

PrEditor3D: Fast and Precise 3D Shape Editing

ArCSEM: Artistic Colorization of SEM Images via Gaussian Splatting

Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images

GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions

Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal

SeamlessNeRF: Stitching Part NeRFs with Gradient Propagation

OCR Graph Features for Manipulation Detection in Documents

ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field

Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions

Make It So: Steering StyleGAN for Any Image Inversion and Editing

FLAME: Free-form Language-based Motion Synthesis & Editing

TreEnhance: A Tree Search Method For Low-Light Image Enhancement

Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization

E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion

Self-Adversarial Training incorporating Forgery Attention for Image Forgery Localization

Stitch it in Time: GAN-Based Facial Editing of Real Videos

Improved StyleGAN Embedding: Where are the Good Latents?

Deep Saliency Prior for Reducing Visual Distraction

LARGE: Latent-Based Regression through GAN Semantics

MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network

Fast Universal Style Transfer for Artistic and Photorealistic Rendering

Passive Classification of Source Printer using Text-line-level Geometric Distortion Signatures from Scanned Images of Printed Documents

Fast Patch-based Style Transfer of Arbitrary Style

From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation Performance

SPARED: Reasoning-Based AI-Generated Image Detection via Adversarially Edited Data

Model the Edit, Not the Image: Visual Autoregressive Editing from a Source-Centric Perspective

Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization

OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing

NullEdit: Stealthy Image Protection via VLM Condition Redirection