GenPose: Generative Category-level Object Pose Estimation via Diffusion Models

TL;DR

This paper introduces GenPose, a novel generative approach using diffusion models for category-level object pose estimation, effectively handling partial observations and generalizing to new categories with state-of-the-art accuracy.

Contribution

It reframes pose estimation as a conditional generative modeling task with a diffusion model, introducing an efficient likelihood estimation method and demonstrating superior performance.

Findings

Achieves over 50% accuracy on strict metrics on REAL275 dataset.

Generalizes well to unseen categories sharing symmetric properties.

Adapts effectively to object pose tracking tasks.

Abstract

Object pose estimation plays a vital role in embodied AI and computer vision, enabling intelligent agents to comprehend and interact with their surroundings. Despite the practicality of category-level pose estimation, current approaches encounter challenges with partially observed point clouds, known as the multihypothesis issue. In this study, we propose a novel solution by reframing categorylevel object pose estimation as conditional generative modeling, departing from traditional point-to-point regression. Leveraging score-based diffusion models, we estimate object poses by sampling candidates from the diffusion model and aggregating them through a two-step process: filtering out outliers via likelihood estimation and subsequently mean-pooling the remaining candidates. To avoid the costly integration process when estimating the likelihood, we introduce an alternative method that trains an energy-based model from the original score-based model, enabling end-to-end likelihood estimation. Our approach achieves state-of-the-art performance on the REAL275 dataset, surpassing 50% and 60% on strict 5d2cm and 5d5cm metrics, respectively. Furthermore, our method demonstrates strong generalizability to novel categories sharing similar symmetric properties without fine-tuning and can readily adapt to object pose tracking tasks, yielding comparable results to the current state-of-the-art baselines.