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。

2025-09-05 至 2025-09-05 共收录 3 篇信号源：cs.CV, cs.GR, cs.MM

1. 效率与蒸馏 3 篇

2509.04406 2025-09-05 cs.CV 57%

Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

Zanwei Zhou, Taoran Yi, Jiemin Fang, Chen Yang, Lingxi Xie, Xinggang Wang, Wei Shen, Qi Tian

机构 * Shanghai Jiao Tong University（上海交通大学）； Huazhong University of Science and Technology（华中科技大学）； Huawei Inc.（华为公司）

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

Comments Project page: https://github.com/Zanue/MDT-dist

2509.04394 2025-09-05 cs.LG cs.CV 57%

Transition Models: Rethinking the Generative Learning Objective

Zidong Wang, Yiyuan Zhang, Xiaoyu Yue, Xiangyu Yue, Yangguang Li, Wanli Ouyang, Lei Bai

机构 * MMLab, CUHK（CUHK人工智能实验室）； Shanghai AI Lab（上海人工智能实验室）； USYD（新南威尔士大学）

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

Comments The code is released at https://github.com/WZDTHU/TiM

2407.15161 2025-09-05 cs.RO cs.AI cs.LG 50%

FFHFlow: Diverse and Uncertainty-Aware Dexterous Grasp Generation via Flow Variational Inference

Qian Feng, Jianxiang Feng, Zhaopeng Chen, Rudolph Triebel, Alois Knoll

机构 * School of Information Computation and Technology, Technical University of Munich (TUM)（技术大学慕尼黑信息计算技术学院）； Institute of Robotics and Mechatronics, German Aerospace Center (DLR)（德国航空航天中心机器人与机电研究所）； Department of Informatics, Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院信息学院）

专题命中效率与蒸馏：diffusion(abstract)

Comments First two authors contributed equally, whose ordering decided via coin-tossing. Accepted for CoRL 2025