PRISM: Learning Realistic Depth via Physics-Grounded Noise Disentanglement with
Overview
PRISM is a tripartite framework that disentangles depth noise into sensing invalidation and measurement inaccuracy, enabling physics-based reasoning. It achieves state-of-the-art fidelity in noisy depth synthesis and a 92.1% success rate in real-world robotic tasks through hierarchical positive-prioritized supervision.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · noise modalities: 2 other · Basis not reported
“k, we introduce a physics-grounded paradigm that disentangles monolithic noise into two complementary modalities: \textbf{sensing invalidation} and \textbf{measurement inaccuracy}, enabling a tailored treatment of noise sources based on their physical origins. Building on this insight, we propose \textbf{PRISM}, a tripartite framework that distills 3D Visual Foundation Model features as rich spatial-semantic priors f”
Exact source · revision 1Source owner not reported
Evidence dependency changes (2)
- 2026-10-30T21:35:48.639Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T21:35:24.771Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalPRISM: Learning Realistic Depth via Physics-Grounded Noise Disentanglement with Semantic-Geometric Collaboration
PRISM is a tripartite framework that disentangles depth noise into sensing invalidation and measurement inaccuracy, enabling physics-based reasoning. It achieves state-of-the-art fidelity in noisy depth synthesis and a 92.1% success rate in real-world robotic tasks through hierarchical positive-prioritized supervision.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).