Utonia: Toward One Encoder for All Point Clouds
Utonia trains a single self-supervised point transformer encoder across diverse point cloud domains to learn unified representations that improve cross-domain perception, embodied reasoning, and robotic manipulation.
Published Mar 3, 2026▲ 189 on Hugging FaceCode ★ 755arXiv ↗
Only vote on papers you've read. Sign in with GitHub to vote.
Utonia delivers compelling cross-domain gains in robot policies and spatial reasoning, but without density ablations, frozen-encoder proof, or inference benchmarks it remains an ambitious first step rather than a verified universal encoder.
Abstract
We dream of a future where point clouds from all domains can come together to shape a single model that benefits them all. Toward this goal, we present Utonia, a first step toward training a single self-supervised point transformer encoder across diverse domains, spanning remote sensing, outdoor LiDAR, indoor RGB-D sequences, object-centric CAD models, and point clouds lifted from RGB-only videos. Despite their distinct sensing geometries, densities, and priors, Utonia learns a consistent representation space that transfers across domains. This unification improves perception capability while revealing intriguing emergent behaviors that arise only when domains are trained jointly. Beyond perception, we observe that Utonia representations can also benefit embodied and multimodal reasoning: conditioning vision-language-action policies on Utonia features improves robotic manipulation, and integrating them into vision-language models yields gains on spatial reasoning. We hope Utonia can serve as a step toward foundation models for sparse 3D data, and support downstream applications in AR/VR, robotics, and autonomous driving.