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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| 3D Semantic Segmentation | ScanNet200 (val) | mIoU (All Classes)13.3 | 25 | |
| 3D Semantic Segmentation | ScanNet20 (val) | mIoU50.7 | 13 | |
| 3D Semantic Segmentation | ScanNet40 (val) | mIoU36.2 | 11 | |
| 3D Semantic Segmentation | ScanNet 20 (val) | mIoU50.7 | 7 |