Any6D：新型物体的无模型6D姿态估计

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

我们推出Any6D，一种无需模型的六维物体姿态估计框架，仅需单张RGB-D锚点图像即可估算新场景中未知物体的六维姿态及尺寸。与依赖纹理化三维模型或多视角的现有方法不同，Any6D通过联合物体对齐过程，强化了二维到三维的对齐及度量尺度估计，从而提升了姿态估计的精确度。我们的方法融合了渲染-比较策略，以生成并优化姿态假设，确保在遮挡、非重叠视角、多样光照条件及大范围跨环境变化等复杂场景下仍能保持稳健性能。我们在五个具有挑战性的数据集——REAL275、Toyota-Light、HO3D、YCBINEOAT和LM-O上进行了评估，结果表明，Any6D在新型物体姿态估计方面显著超越了当前最先进的方法，展现了其卓越效能。项目页面：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