仅用未贴图3D模型实现无训练的6D姿态估计，抗缺陷、抗光照变化。
PIXIE: A Zero-Shot texture-invariant 6D pose estimation framework for unseen objects with assembly defects
- 基于合成深度与法线图匹配，仅依赖几何信息进行姿态推断。
- 在无纹理物体上达到顶尖性能，且对装配缺陷和遮挡鲁棒。
- 适合工业场景中未知物体的快速部署，无需定制训练数据。
6D姿态估计是机器人与计算机视觉中的关键技术，尤其在工业环境中面临挑战。现有数据驱动方法常受限于资源密集的数据流程、对纹理化3D模型的依赖，以及对损伤或装配缺陷引起的几何偏差敏感。本文提出PIXIE，一种零样本框架，仅需未贴图3D模型即可从单张RGB图像估计物体6D姿态。通过从采样参考视角渲染合成深度图与法线图，并利用预训练跨模态特征匹配器与查询图像匹配，提取对应点后反投影得到2D-3D对应关系，进而基于PnP算法估计姿态。该方法完全依赖几何信息，天然具备对抗光照与纹理变化的能力，同时通过对应点过滤处理模型与实物间的几何偏差。我们在多个公开基准上评估，对无纹理物体实现了当前最优结果；并引入一个包含装配缺陷、纹理变化与遮挡的新数据集，验证其真实世界适用性。
原文摘要 · Abstract (English)
6D pose estimation remains a key challenge in robotics and computer vision, particularly in industrial environments. The deployment of currently available data-driven methods is often limited by resource-intensive data pipelines, reliance on textured 3D models, and sensitivity to geometric deviations caused by damages or assembly defects. We present PIXIE, a zero-shot framework that estimates the 6D pose of an object from an RGB image using only an untextured 3D model. Synthetic depth and normal maps are rendered from sampled reference viewpoints and matched to the query image via a pretrained cross-modality feature matcher. Matched keypoints are back-projected to obtain 2D--3D correspondences for PnP-based pose estimation. Relying exclusively on geometry makes the method inherently robust to lighting and texture variation, while correspondence filtering handles geometric deviations between the model and physical object. We evaluate on widely-used public benchmarks, reporting state-of-the-art results on texture-less objects without object-specific training, and introduce a novel dataset with assembly defects, texture variations, and occlusion to demonstrate real-world applicability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。