{"ID":2873151,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.07978","arxiv_id":"2509.07978","title":"One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation","abstract":"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/","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2509.07978","url_pdf":"https://arxiv.org/pdf/2509.07978v1","authors":"[\"Zheng Geng\",\"Nan Wang\",\"Shaocong Xu\",\"Chongjie Ye\",\"Bohan Li\",\"Zhaoxi Chen\",\"Sida Peng\",\"Hao Zhao\"]","published":"2025-09-09T17:59:02Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}