图像生成

A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations

Junwei Su, Chuan Wu

机构 * School of Computing（计算学院） ； Data Science, University of Hong Kong（数据科学，香港大学） 纠错

专题命中 扩散模型 ：diffusion(abstract)

3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation

Nikolaos Gkanatsios, Jiahe Xu, Matthew Bronars, Arsalan Mousavian, Tsung-Wei Ke, Katerina Fragkiadaki

机构 * Carnegie Mellon University（卡内基梅隆大学） ； NVIDIA（英伟达） ； National Taiwan University（国立台湾大学） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Comments Project page: https://3d-flowmatch-actor.github.io/

Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions

Jaeyeon Kim, Kulin Shah, Vasilis Kontonis, Sham Kakade, Sitan Chen

机构 * Harvard University（哈佛大学） ； University of Texas Austin（德克萨斯大学奥斯汀分校） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Further improving quantum algorithms for nonlinear differential equations via higher-order methods and rescaling

Pedro C. S. Costa, Philipp Schleich, Mauro E. S. Morales, Dominic W. Berry

专题命中 扩散模型 ：diffusion(abstract)

Comments 37 pages, 2 figures

Journal ref npj Quantum Information 11, 141 (2025)

MUSE: Multi-Subject Unified Synthesis via Explicit Layout Semantic Expansion

Fei Peng, Junqiang Wu, Yan Li, Tingting Gao, Di Zhang, Huiyuan Fu

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Kuaishou Technology（快手科技） 纠错

专题命中 可控生成 ：text-to-image(abstract)；diffusion(abstract)；image synthesis(abstract)；分类 cs.CV

Comments This paper is accepted by ICCV 2025

TransLight: Image-Guided Customized Lighting Control with Generative Decoupling

Zongming Li, Lianghui Zhu, Haocheng Shen, Longjin Ran, Wenyu Liu, Xinggang Wang

机构 * OpenAI 纠错

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

Comments 15 pages, 9 figures

SimGenHOI: Physically Realistic Whole-Body Humanoid-Object Interaction via Generative Modeling and Reinforcement Learning

Yuhang Lin, Yijia Xie, Jiahong Xie, Yuehao Huang, Ruoyu Wang, Jiajun Lv, Yukai Ma, Xingxing Zuo

专题命中 可控生成 ：diffusion(abstract)

AnchorSync: Global Consistency Optimization for Long Video Editing

Zichi Liu, Yinggui Wang, Tao Wei, Chao Ma

机构 * MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University Shanghai China（人工智能联合实验室，人工智能研究院，上海交通大学） 纠错

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

Comments ACM MM 2025; Code is released at https://github.com/VISION-SJTU/AnchorSync

2D Gaussians Meet Visual Tokenizer

Yiang Shi, Xiaoyang Guo, Wei Yin, Mingkai Jia, Qian Zhang, Xiaolin Hu, Wenyu Liu, Xinggang Wang

机构 * Huazhong University of Science and Technology（华中科技大学） ； Horizon Robotics ； Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） 纠错

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

Img2ST-Net: Efficient High-Resolution Spatial Omics Prediction from Whole Slide Histology Images via Fully Convolutional Image-to-Image Learning

Junchao Zhu, Ruining Deng, Junlin Guo, Tianyuan Yao, Juming Xiong, Chongyu Qu, Mengmeng Yin, Yu Wang, Shilin Zhao, Haichun Yang, Daguang Xu, Yucheng Tang, Yuankai Huo

机构 * Department of Computer Science, Vanderbilt University（计算机科学系，范德比尔特大学） ； Weill Cornell Medicine（韦尔·科恩医学中心） ； Department of Electrical and Computer Engineering, Vanderbilt University（电气与计算机工程系，范德比尔特大学） ； Department of Biostatistics, Vanderbilt University Medical Center（生物统计学系，范德比尔特大学医学中心） ； NVIDIA 纠错

专题命中 效率与蒸馏 ：image generation(abstract)；分类 cs.CV

Multimode Fiber Imaging Based on Hydrogel Fiber

Lele He, Mengchao Cao, Lili Gui, Jingjing Guo, Xiaosheng Xiao

专题命中 其他图像生成 ：image generation(abstract)

Comments The main content has been published in 2024 22nd ICOCN (10.1109/ICOCN63276.2024.10648561), and this article provides more detailed information (see the supplementary files)