仅用一张图实现精准3D物体姿态估计，解决真实场景下的泛化难题。
One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation
- 通过多视角特征匹配与渲染对比优化，逐步精修姿态与尺度。
- 在YCBInEOAT等数据集上超越现有方法，姿态误差降低27%以上。
- 适合机器人抓取、少样本三维重建等实际应用需求。
从单张参考图像中估计任意未见过物体的6自由度姿态，对机器人在长尾真实场景中的操作至关重要。然而该任务极具挑战：3D模型通常不可得，单视图重建缺乏度量尺度，且合成数据与真实图像间的域差距削弱了鲁棒性。我们提出OnePoseViaGen，通过两个关键组件应对这些挑战：首先，采用粗到精的对齐模块，结合多视角特征匹配与渲染-对比优化，联合精修尺度与姿态；其次，引入文本引导的生成域随机化策略，多样化纹理，使姿态估计算法可通过合成数据有效微调。上述步骤共同实现高保真单视图3D生成，支持可靠的单次6D姿态估计。在挑战性基准（YCBInEOAT、Toyota-Light、LM-O）上，OnePoseViaGen性能显著优于此前方法。进一步实验验证了其在真实机械手灵巧抓取中的实用性。
原文摘要 · Abstract (English)
Estimating the 6D pose of arbitrary unseen objects from a single reference image is critical for robotics operating in the long-tail of real-world instances. However, this setting is notoriously challenging: 3D models are rarely available, single-view reconstructions lack metric scale, and domain gaps between generated models and real-world images undermine robustness. We propose OnePoseViaGen, a pipeline that tackles these challenges through two key components. First, a coarse-to-fine alignment module jointly refines scale and pose by combining multi-view feature matching with render-and-compare refinement. Second, a text-guided generative domain randomization strategy diversifies textures, enabling effective fine-tuning of pose estimators with synthetic data. Together, these steps allow high-fidelity single-view 3D generation to support reliable one-shot 6D pose estimation. On challenging benchmarks (YCBInEOAT, Toyota-Light, LM-O), OnePoseViaGen achieves state-of-the-art performance far surpassing prior approaches. We further demonstrate robust dexterous grasping with a real robot hand, validating the practicality of our method in real-world manipulation. Project page: https://gzwsama.github.io/OnePoseviaGen.github.io/
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。