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

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 multi-hypothesis issue. In this study, we propose a novel solution by reframing category-level 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 and demonstrates promising generalizability to novel categories sharing similar symmetric properties without fine-tuning. Furthermore, it can readily adapt to object pose tracking tasks, yielding comparable results to the current state-of-the-art baselines. Our checkpoints and demonstrations can be found at https://sites.google.com/view/genpose.