3D 视觉

LSS3D: Learnable Spatial Shifting for Consistent and High-Quality 3D Generation from Single-Image

Zhuojiang Cai, Yiheng Zhang, Meitong Guo, Mingdao Wang, Yuwang Wang

机构 * Tsinghua University, Beijing, China（清华大学） ； Beihang University, Beijing, China（北航） ； National University of Singapore, Singapore（国立新加坡大学） 纠错

专题命中 3D生成 ：3D generation(title,abstract)；分类 cs.CV

AnchorDS: Anchoring Dynamic Sources for Semantically Consistent Text-to-3D Generation

Jiayin Zhu, Linlin Yang, Yicong Li, Angela Yao

专题命中 3D生成 ：3D generation(title)；分类 cs.CV

Comments Accepted by AAAI 2026. Project page: https://jyzhu.top/AnchorDS_Webpage/

PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image

Ziang Cao, Fangzhou Hong, Zhaoxi Chen, Liang Pan, Ziwei Liu

机构 * S-Lab, Nanyang Technological University（南洋理工大学S实验室） ； Shanghai AI Lab（上海人工智能实验室） 纠错

专题命中 3D生成 ：3D generation(abstract)；分类 cs.CV、cs.RO

Comments Project page: https://physx-anything.github.io/

Optimizing Input of Denoising Score Matching is Biased Towards Higher Score Norm

Tongda Xu

机构 * AIR & CST, Tsinghua University（人工智能研究院与计算科学与技术系，清华大学） 纠错

专题命中 3D生成 ：3D generation(abstract)；分类 cs.CV

Comments NIPS 25 Workshop: Frontiers in Probabilistic Inference: Sampling Meets Learning