|
|
Tsinghua Spatial Intelligence Lab (THUSI Lab)
|
|
*Equal contribution †Project leader |
![[Image Description]](./base/Fast3Dcache.png)
|
Mengyu Yang, Yanming Yang , Chenyi Xu , Chenxi Song , Yufan Zuo , Tong Zhao , Ruibo Li , Chi Zhang [CVPR 2026] [arXiv] [Code] [Project Page] We propose Fast3Dcache, a training-free geometry-aware caching framework that accelerates 3D diffusion inference while preserving geometric fidelity. Comprehensive experiments show that Fast3Dcache accelerates inference significantly, achieving up to a 27.12% speed-up and a 54.83% reduction in FLOPs, with minimal degradation in geometric quality as measured by Chamfer Distance (2.48%) and F-Score (1.95%). |
|
|
|
|