{"ID":2833124,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.05044","arxiv_id":"2512.05044","title":"Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image","abstract":"Generating interactive and dynamic 4D scenes from a single static image remains a core challenge. Most existing generate-then-reconstruct and reconstruct-then-generate methods decouple geometry from motion, causing spatiotemporal inconsistencies and poor generalization. To address these, we extend the reconstruct-then-generate framework to jointly perform Motion generation and geometric Reconstruction for 4D Synthesis (MoRe4D). We first introduce TrajScene-60K, a large-scale dataset of 60,000 video samples with dense point trajectories, addressing the scarcity of high-quality 4D scene data. Based on this, we propose a diffusion-based 4D Scene Trajectory Generator (4D-STraG) to jointly generate geometrically consistent and motion-plausible 4D point trajectories. To leverage single-view priors, we design a depth-guided motion normalization strategy and a motion-aware module for effective geometry and dynamics integration. We then propose a 4D View Synthesis Module (4D-ViSM) to render videos with arbitrary camera trajectories from 4D point track representations. Experiments show that MoRe4D generates high-quality 4D scenes with multi-view consistency and rich dynamic details from a single image. Code: https://github.com/Zhangyr2022/MoRe4D.","short_abstract":"Generating interactive and dynamic 4D scenes from a single static image remains a core challenge. Most existing generate-then-reconstruct and reconstruct-then-generate methods decouple geometry from motion, causing spatiotemporal inconsistencies and poor generalization. To address these, we extend the reconstruct-then-...","url_abs":"https://arxiv.org/abs/2512.05044","url_pdf":"https://arxiv.org/pdf/2512.05044v1","authors":"[\"Yanran Zhang\",\"Ziyi Wang\",\"Wenzhao Zheng\",\"Zheng Zhu\",\"Jie Zhou\",\"Jiwen Lu\"]","published":"2025-12-04T17:59:10Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":606298,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2833124,"paper_url":"https://arxiv.org/abs/2512.05044","paper_title":"Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image","repo_url":"https://github.com/Zhangyr2022/MoRe4D","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}