UniRecGen: Unifying Multi-View 3D Reconstruction and Generation

TL;DR

UniRecGen is a unified framework combining 3D reconstruction and diffusion-based generation to produce complete, consistent 3D models from sparse views, leveraging shared canonical space and cooperative learning.

Contribution

It introduces a cooperative system that unifies reconstruction and generation in a shared space, improving 3D modeling from sparse observations.

Findings

Outperforms existing methods in fidelity and robustness.

Produces complete and consistent 3D models from sparse views.

Demonstrates effective collaboration between reconstruction and diffusion models.

Abstract

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.