CVPR 2025

We introduce Any6D, a model-free framework for 6D object pose estimation that requires only a single RGB-D anchor image to estimate both the 6D pose and size of unknown objects in novel scenes. Unlike existing methods that rely on textured 3D models or multiple viewpoints, Any6D leverages a joint object alignment process to enhance 2D-3D alignment and metric scale estimation for improved pose accuracy. Our approach integrates a render-and-compare strategy to generate and refine pose hypotheses, enabling robust performance in scenarios with occlusions, non-overlapping views, diverse lighting conditions, and large cross-environment variations. We evaluate our method on five challenging datasets: REAL275, Toyota-Light, HO3D, YCBINEOAT, and LM-O, demonstrating its effectiveness in significantly outperforming state-of-the-art methods for novel object pose estimation.

Overview of the Any6D framework for model-free object pose estimation. First, we reconstruct the normalized object shape O_N from the image-to-3D model. Then, we estimate accurate object pose and size from anchor image I_A using the proposed object alignment. Next, we use the query image I_Q to estimate the pose with the reconstructed metric-scale object shape O_M.