Jul 2026
HyperGS: Fast and Generalizable Gaussian Video Representation
This work proposes HyperGS, a feedforward, optimization-free approach that directly predicts Gaussian representations from any video in a single forward pass, speeding up encoding and decoding by orders of magnitude while generalizing to out-of-distribution videos at higher resolutions.
Fatima Zohra, Chen Zhao, Shuming Liu et al.
· arXiv.org · 0 citations