This website accompanies the research paper:
Velox: Learning Representations of 4D Geometry and Appearance, CVPR 2026.
Anagh Malik, Dorian Chan, Xiaoming Zhao, David B. Lindell, Oncel Tuzel, Jen-Hao Rick Chang
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. Please see the website for video results.
- Repository is released under LICENSE.
- All generated samples provided here are licensed under LICENSE_DATA.
Our codebase is built using multiple opensource contributions, please see ACKNOWLEDGEMENTS for more details.
@inproceedings{malik2025velox,
author = {Malik, Anagh and Chan, Dorian and Zhao, Xiaoming and Lindell, David B. and Tuzel, Oncel and Chang, Jen-Hao Rick},
title = {Velox: Learning Representations of 4D Geometry and Appearance},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2026}
}