2026/04/01 by Zhisheng Huang, Jiahao Chen, Cheng Lin +10 · 1 voice
Computer Science · Engineering · #3D Shape Modeling and Analysis #3D reconstruction #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Fidelity #Generative grammar #Generator (circuit theory) #High fidelity #Iterative reconstruction #Prior probability #Solid modeling #cs.CV
paper · pdf · open access · doi:10.48550/arxiv.2604.01479
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2026/04/01 · arxiv published 2026/04/01 · arxiv updated 2026/04/03 · openalex created_date 2026/04/04 · openalex updated_date 2026/07/28
Sparse-view 3D modeling represents a fundamental tension between reconstruction fidelity and generative plausibility. While feed-forward reconstruction excels in efficiency and input alignment, it often lacks the global priors needed for structural completeness. Conversely, diffusion-based generation provides rich geometric details but struggles with multi-view consistency. We present UniRecGen, a unified framework that integrates these two paradigms into a single cooperative system. To overcome inherent conflicts in coordinate spaces, 3D representations, and training objectives, we align both models within a shared canonical space. We employ disentangled cooperative learning, which maintains stable training while enabling seamless collaboration during inference. Specifically, the reconstruction module is adapted to provide canonical geometric anchors, while the diffusion generator leverages latent-augmented conditioning to refine and complete the geometric structure. Experimental results demonstrate that UniRecGen achieves superior fidelity and robustness, outperforming existing methods in creating complete and consistent 3D models from sparse observations. Code is available at https://github.com/zsh523/UniRecGen.