Article

PRISM Achieves Realistic Depth Synthesis via Physical Noise Disentanglement, with 92.1% Average Success Rate on Real-Robot Tasks

The paper proposes the PRISM framework, which disentangles depth noise into two modalities—sensing invalidation and measurement inaccuracy—and distills features from 3D visual foundation models as spatial-semantic priors.

Part of the event: PRISM Uses Physical Noise Disentanglement to Improve Depth Synthesis Realism

This page provides a summary and source link only.