Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Privacy-Preserving Depth-Only Open-Vocabulary 3D Semantic Segmentation Via Uncertainty-Guided Test-Time Optimization

About

Privacy-preserving perception is a critical requirement for deploying 3D scene understanding systems in real-world indoor environments, yet it remains underexplored in open-vocabulary 3D semantic segmentation. Existing methods typically rely on obtaining rich semantic cues from RGB images, which may expose privacy-sensitive visual information. Depth-only 3D geometry provides a privacy-preserving alternative, but the absence of appearance-based semantic cues makes open-vocabulary predictions highly uncertain and less reliable. Under this setting, we propose to convert uncertainty into a guidance signal to identify unreliable semantic responses and use semantic priors from foundation models to regularize their refinement. We present UTTO, an uncertainty-guided test-time optimization framework for depth-only open-vocabulary 3D semantic segmentation. Without additional training, experiments on ScanNet20, ScanNet40, and ScanNet200 demonstrate that UTTO consistently improves depth-only open-vocabulary 3D segmentation and outperforms representative baselines under privacy-preserving conditions.

Xuying Huang, Sicong Pan, Maren Bennewitz• 2026

Related benchmarks

TaskDatasetResultRank
3D Semantic SegmentationScanNet200 (val)
mIoU (All Classes)13.3
25
3D Semantic SegmentationScanNet20 (val)
mIoU50.7
13
3D Semantic SegmentationScanNet40 (val)
mIoU36.2
11
3D Semantic SegmentationScanNet 20 (val)
mIoU50.7
7
Showing 4 of 4 rows

Other info

Follow for update