Any6D：新型物件的無模型六維姿態估計

Any6D: Model-free 6D Pose Estimation of Novel Objects

March 24, 2025

作者: Taeyeop Lee, Bowen Wen, Minjun Kang, Gyuree Kang, In So Kweon, Kuk-Jin Yoon

cs.AI

摘要

我們提出了Any6D，這是一個無需模型的六維物體姿態估計框架，僅需單張RGB-D錨點圖像即可估算新場景中未知物體的六維姿態和尺寸。與依賴於紋理化3D模型或多視角的現有方法不同，Any6D利用聯合物體對齊過程來增強2D-3D對齊和度量尺度估計，從而提高姿態精度。我們的方法整合了渲染-比較策略，以生成並優化姿態假設，使其在遮擋、非重疊視角、多樣光照條件及大跨環境變化的場景中展現出強健性能。我們在五個具有挑戰性的數據集上評估了該方法：REAL275、Toyota-Light、HO3D、YCBINEOAT和LM-O，結果顯示其在顯著超越新物體姿態估計領域最新技術方面具有顯著效果。項目頁面：https://taeyeop.com/any6d

English

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. Project page: https://taeyeop.com/any6d