UniRecGen：统一多视角三维重建与生成

摘要

稀疏视角三维建模始终面临着重建保真度与生成合理性之间的根本性矛盾。前馈重建方法虽在效率和输入对齐方面表现出色，却常因缺乏全局先验知识而难以保证结构完整性；反之，基于扩散的生成方法能提供丰富的几何细节，却在多视角一致性方面存在不足。我们提出的UniRecGen框架将这两种范式整合为协同工作的统一系统。为克服坐标空间、三维表征和训练目标的内在冲突，我们将双模型对齐至共享规范空间。通过解耦式协同学习策略，在保持训练稳定性的同时实现推理阶段的无缝协作：重建模块经适配后提供规范几何锚点，而扩散生成器则利用潜在增强条件机制对几何结构进行细化补全。实验结果表明，UniRecGen在稀疏观测数据下能生成更完整、一致的三维模型，在保真度与鲁棒性方面均优于现有方法。

English

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.

UniRecGen：统一多视角三维重建与生成

UniRecGen: Unifying Multi-View 3D Reconstruction and Generation

摘要

Support