MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation

TL;DR

MAPRPose is a novel two-stage framework for multi-object 6D pose estimation that effectively handles occlusion and noise, achieving state-of-the-art accuracy and significant speed improvements.

Contribution

It introduces mask-aware correspondences for pose proposal and an amodal-driven refinement pipeline with GPU acceleration, advancing robustness and efficiency in pose estimation.

Findings

Achieves 76.5% AR on BOP benchmark, outperforming FoundationPose by 3.1%.

Provides 43x faster multi-object inference speed.

Utilizes a tensorized render-and-compare pipeline for robust refinement.

Abstract

6D object pose estimation in cluttered scenes remains challenging due to severe occlusion and sensor noise. We propose MAPRPose, a two-stage framework that leverages mask-aware correspondences for pose proposal and amodal-driven Region-of-Interest (ROI) prediction for robust refinement. In the Mask-Aware Pose Proposal (MAPP) stage, we lift 2D correspondences into 3D space to establish reliable keypoint matches and generate geometrically consistent pose hypotheses based on correspondence-level scoring, from which the top-$K$ candidates are selected. In the refinement stage, we introduce a tensorized render-and-compare pipeline integrated with an Amodal Mask Prediction and ROI Re-Alignment (AMPR) module. By reconstructing complete object geometry and dynamically adjusting the ROI, AMPR mitigates localization errors and spatial misalignment under heavy occlusion. Furthermore, our GPU-accelerated RGB-XYZ reprojection enables simultaneous refinement of all $N \times B$ pose hypotheses in a single forward pass. Evaluated on the BOP benchmark, MAPRPose achieves a state-of-the-art Average Recall (AR) of 76.5%, outperforming FoundationPose by 3.1% AR while delivering a 43x speedup in multi-object inference.