Uncertainty-guided test-time optimization boosts depth-only 3D segmentation
UTTO uses predictive uncertainty as a signal to test-time optimize a frozen open-vocabulary 3D segmentation backbone, yielding consistent gains on ScanNet and Matterport3D.
ImportanceLocalEvidenceE2 unreplicated
Indoor robots can now do open-vocabulary 3D segmentation from depth alone in privacy-preserving settings where RGB is banned: UTTO uses predictive uncertainty as a signal to test-time optimize a frozen open-vocabulary 3D segmentation backbone, and the authors report consistent gains across multiple depth-only backbones on ScanNet and Matterport3D.
Previously such settings had to rely on RGB or retrain the backbone, and segmentation quality suffered when RGB was banned.
The result is self-reported by Huang and two other authors, with a privacy-recoverability analysis and a real-robot case study; no independent reproduction has yet appeared, and the paper was first submitted on July 1, 2026 and updated to v2 on September 17 (arXiv:2607.00978).
Source: arXiv:2607.00978 abstract page (v2, updated 2026-09-17) ↗