Velox: Learning Representations of 4D Geometry and Appearance
Anagh Malik, Dorian Chan, Xiaoming Zhao, David B. Lindell, Oncel Tuzel, Jen-Hao Rick Chang
Abstract
We introduce a framework for learning latent representations of 4D objects which are descriptive, faithfully capturing object geometry and appearance; compressive, aiding in downstream efficiency; and accessible, requiring minimal input, i.e., an unstructured dynamic point cloud, to construct. Specifically, Velox trains an encoder to compress spatiotemporal color point clouds into a set of dynamic tokens. These tokens are supervised using two complementary decoders: a 4D surface decoder, which models the time-varying surface distribution capturing the geometry; and a Gaussian decoder, which maps the tokens to 3D Gaussians, helping learn appearance. To demonstrate the utility of our representation, we evaluate it across three downstream tasks: video-to-4D generation, 3D tracking, and cloth simulation via image-to-4D generation, and observe strong performances in all settings.
BibTeX
@inproceedings{cvpr2026_veloxlearningrep,
title = {Velox: Learning Representations of 4D Geometry and Appearance},
author = {Anagh Malik and Dorian Chan and Xiaoming Zhao and David B. Lindell and Oncel Tuzel and Jen-Hao Rick Chang},
booktitle = {CVPR 2026},
year = {2026}
}