arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

图像生成

图像生成、文生图、图像编辑、扩散模型和可控生成。

2025-07-31 至 2025-07-31 共收录 41 信号源:cs.CV, cs.GR, cs.MM

1. 扩散模型 29 篇

2412.12308 2025-07-31 math.NA cs.NA physics.comp-ph 50%

Numerical Solution Partial Differential Equations using the Discrete Fourier Transform

Daniela Rodriguez-Lara, Ivan Alvarez-Rios, Francisco S. Guzman

专题命中 扩散模型 :diffusion(abstract)

Comments Prepared for educational purposes, 9 pages, 9 figures. Accepted for publication in the educative section of Revista Mexicana de Fisica

Journal ref Rev. Mex. Fis. E 22, 020221 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.07501 2025-07-31 cs.LG physics.bio-ph q-bio.QM 50%

Inferring biological processes with intrinsic noise from cross-sectional data

Suryanarayana Maddu, Victor Chardès, Michael. J. Shelley

机构 * Center for Computational Biology, Flatiron Institute, New York, NY, USA, 10010(计算生物学中心,Flatiron研究所,纽约,纽约州,美国,10010) Courant Institute of Mathematical Sciences, New York University, New York, NY, USA, 10012(数学科学学院,纽约大学,纽约,纽约州,美国,10012)

专题命中 扩散模型 :diffusion(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2207.10185 2025-07-31 cs.LG 50%

An Introduction to Modern Statistical Learning

Joseph G. Makin

专题命中 扩散模型 :diffusion(abstract)

Comments Manuscript draft, v. 2.0; 199 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22199 2025-07-31 cond-mat.stat-mech 50%

Self-propulsion symmetries determine entropy production of active particles with hidden states

Jacob Knight, Farid Kaveh, Gunnar Pruessner

专题命中 扩散模型 :diffusion(abstract)

Comments 6 pages main text, 1 figure, 10 pages supplement,

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 可控生成 2 篇

2507.22825 2025-07-31 cs.CV 79%

DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion

Qingcheng Zhao, Xiang Zhang, Haiyang Xu, Zeyuan Chen, Jianwen Xie, Yuan Gao, Zhuowen Tu

机构 * ShanghaiTech University(上海科技大学) UC San Diego(加州大学圣地亚哥分校) Lambda, Inc.(Lambda公司) Stanford University(斯坦福大学)

专题命中 可控生成 :diffusion(title,abstract);分类 cs.CV

Comments ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22003 2025-07-31 cs.CV 57%

See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs

Ziyun Dai, Xiaoqiang Li, Shaohua Zhang, Yuanchen Wu, Jide Li

专题命中 可控生成 :image generation(abstract);分类 cs.CV

Comments Accepted by ACM MM25

Journal ref 33rd ACM International Conference on Multimedia 2025

详情

展开后加载摘要…

URL PDF HTML 收藏

3. 图像修复 1 篇

2311.18348 2025-07-31 physics.geo-ph cs.LG 50%

Reconstructing Historical Climate Fields With Deep Learning

Nils Bochow, Anna Poltronieri, Martin Rypdal, Niklas Boers

机构 * Department of Mathematics and Statistics, Faculty of Science and Technology, UiT - The Arctic University of Norway(乌伊特-北极大学数学与统计学系) Physics of Ice, Climate and Earth, Niels Bohr Institute, University of Copenhagen(哥本哈根大学冰川、气候与地球物理研究所) Potsdam Institute for Climate Impact Research(波茨坦气候影响研究所) Earth System Modelling, School of Engineering, Design, Technical University of Munich(慕尼黑技术大学工程与设计学院) Department of Mathematics and Global Systems Institute, University of Exeter(埃克塞特大学数学与全球系统研究所)

专题命中 图像修复 :inpainting(abstract)

Comments Accepted version + SI

Journal ref Sci. Adv.11,eadp0558(2025)

详情

展开后加载摘要…

URL PDF HTML 收藏

4. 个性化与一致性 3 篇

2504.21646 2025-07-31 cs.CV 79%

Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protection

Liqin Wang, Qianyue Hu, Wei Lu, Xiangyang Luo

机构 * School of Computer Science Engineering, Sun Yat-sen University Guangzhou China State Key Laboratory of Mathematical Engineering Engineering, Sun Yat-sen University

专题命中 个性化与一致性 :diffusion(title,abstract);分类 cs.CV

Comments Accepted by ACM MM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.19776 2025-07-31 cs.CV cs.LG 79%

Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation

Tuna Han Salih Meral, Enis Simsar, Federico Tombari, Pinar Yanardag

机构 * Virginia Tech(弗吉尼亚理工学院) ETH Zürich(苏黎世联邦理工学院) TUM(慕尼黑工业大学) Google(谷歌)

专题命中 个性化与一致性 :image generation(title,abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.02612 2025-07-31 cs.CV 70%

Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation

Jiwoo Chung, Sangeek Hyun, Hyunjun Kim, Eunseo Koh, MinKyu Lee, Jae-Pil Heo

机构 * Sungkyunkwan University(成均馆大学)

专题命中 个性化与一致性 :text-to-image(abstract);diffusion(abstract);分类 cs.CV

Comments Accepted to ICCV 2025. Project page: https://jiwoogit.github.io/ARBooth/

详情

展开后加载摘要…

URL PDF HTML 收藏

5. 其他图像生成 1 篇

2507.17332 2025-07-31 cs.CV 57%

PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image

Hyeongjin Nam, Donghwan Kim, Gyeongsik Moon, Kyoung Mu Lee

机构 * Dept. of ECE&ASRI, Seoul National University(电子工程与先进科学研究所,首尔国立大学) Dept. of CSE, Korea University(计算机科学与工程系,韩国大学)

专题命中 其他图像生成 :image generation(abstract);分类 cs.CV

Comments Published at ICCV 2025, 22 pages including the supplementary material

详情

展开后加载摘要…

URL PDF HTML 收藏