Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation
Yifei Zhu, Mingyi Shi, Yangyang Cai +3
Text-to-motion generation must produce motions that are semantically correct, temporally coherent, and physically plausible. A natural approach is to first project motion data into…
cs.CV2024
Online Neural Path Guiding with Normalized Anisotropic Spherical Gaussians
Jiawei Huang, Akito Iizuka, Hajime Tanaka +2
The variance reduction speed of physically-based rendering is heavily affected by the adopted importance sampling technique. In this paper we propose a novel online framework to le…