Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching
This addresses the problem of object pose estimation for robotics and AR/VR applications by enabling generalization to new objects with minimal data, though it is incremental as it builds on diffusion models for image generation.
The paper tackles single-view object pose estimation by proposing a method that generalizes to unseen objects using only one reference image, without needing 3D models or extensive training, achieving superior performance over existing techniques in synthetic and real-world datasets.
In this paper, we present a novel generalizable object pose estimation method to determine the object pose using only one RGB image. Unlike traditional approaches that rely on instance-level object pose estimation and necessitate extensive training data, our method offers generalization to unseen objects without extensive training, operates with a single reference image of the object, and eliminates the need for 3D object models or multiple views of the object. These characteristics are achieved by utilizing a diffusion model to generate novel-view images and conducting a two-sided matching on these generated images. Quantitative experiments demonstrate the superiority of our method over existing pose estimation techniques across both synthetic and real-world datasets. Remarkably, our approach maintains strong performance even in scenarios with significant viewpoint changes, highlighting its robustness and versatility in challenging conditions. The code will be re leased at https://github.com/scy639/Gen2SM.