Geometrically Plausible Object Pose Refinement using Differentiable Simulation

TL;DR

This paper introduces a multi-modal pose refinement method that uses differentiable physics simulation and rendering to improve the geometric plausibility and accuracy of object poses in manipulation tasks.

Contribution

It presents a novel approach combining differentiable physics, rendering, and visuo-tactile sensing for physically consistent pose refinement, outperforming standard methods.

Findings

Reduces intersection volume error by 73% with accurate initial estimates.

Achieves over 87% reduction in intersection error under high uncertainty.

Improves geometric plausibility while decreasing translation and orientation errors.

Abstract

State-of-the-art object pose estimation methods are prone to generating geometrically infeasible pose hypotheses. This problem is prevalent in dexterous manipulation, where estimated poses often intersect with the robotic hand or are not lying on a support surface. We propose a multi-modal pose refinement approach that combines differentiable physics simulation, differentiable rendering and visuo-tactile sensing to optimize object poses for both spatial accuracy and physical consistency. Simulated experiments show that our approach reduces the intersection volume error between the object and robotic hand by 73\% when the initial estimate is accurate and by over 87\% under high initial uncertainty, significantly outperforming standard ICP-based baselines. Furthermore, the improvement in geometric plausibility is accompanied by a concurrent reduction in translation and orientation errors. Achieving pose estimation that is grounded in physical reality while remaining faithful to multi-modal sensor inputs is a critical step toward robust in-hand manipulation.