Object Pose Estimation via the Aggregation of Diffusion Features
This addresses the limited generalizability in 3D scene understanding for robotics and AR/VR applications, representing a strong specific gain rather than an incremental improvement.
The paper tackles the problem of object pose estimation for unseen objects by introducing diffusion features from models like Stable Diffusion, achieving significant performance improvements with 97.9% vs. 93.5% accuracy on Unseen LM and 85.9% vs. 76.3% on Unseen O-LM.
Estimating the pose of objects from images is a crucial task of 3D scene understanding, and recent approaches have shown promising results on very large benchmarks. However, these methods experience a significant performance drop when dealing with unseen objects. We believe that it results from the limited generalizability of image features. To address this problem, we have an in-depth analysis on the features of diffusion models, e.g. Stable Diffusion, which hold substantial potential for modeling unseen objects. Based on this analysis, we then innovatively introduce these diffusion features for object pose estimation. To achieve this, we propose three distinct architectures that can effectively capture and aggregate diffusion features of different granularity, greatly improving the generalizability of object pose estimation. Our approach outperforms the state-of-the-art methods by a considerable margin on three popular benchmark datasets, LM, O-LM, and T-LESS. In particular, our method achieves higher accuracy than the previous best arts on unseen objects: 97.9% vs. 93.5% on Unseen LM, 85.9% vs. 76.3% on Unseen O-LM, showing the strong generalizability of our method. Our code is released at https://github.com/Tianfu18/diff-feats-pose.