{"ID":2851309,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.20776","arxiv_id":"2510.20776","title":"CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling","abstract":"We introduce Cupid, a generative 3D reconstruction framework that jointly models the full distribution over both canonical objects and camera poses. Our two-stage flow-based model first generates a coarse 3D structure and 2D-3D correspondences to estimate the camera pose robustly. Conditioned on this pose, a refinement stage injects pixel-aligned image features directly into the generative process, marrying the rich prior of a generative model with the geometric fidelity of reconstruction. This strategy achieves exceptional faithfulness, outperforming state-of-the-art reconstruction methods by over 3 dB PSNR and 10% in Chamfer Distance. As a unified generative model that decouples the object and camera pose, Cupid naturally extends to multi-view and scene-level reconstruction tasks without requiring post-hoc optimization or fine-tuning.","short_abstract":"We introduce Cupid, a generative 3D reconstruction framework that jointly models the full distribution over both canonical objects and camera poses. Our two-stage flow-based model first generates a coarse 3D structure and 2D-3D correspondences to estimate the camera pose robustly. Conditioned on this pose, a refinement...","url_abs":"https://arxiv.org/abs/2510.20776","url_pdf":"https://arxiv.org/pdf/2510.20776v2","authors":"[\"Binbin Huang\",\"Haobin Duan\",\"Yiqun Zhao\",\"Zibo Zhao\",\"Yi Ma\",\"Shenghua Gao\"]","published":"2025-10-23T17:47:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}