用多视角外推重建稀疏视图3D场景，保持几何一致且速度快。
GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction
- 通过扩展已有视角视野而非生成新视角，保证几何一致性。
- 在3、6、9个输入视角下均实现高质量重建，最快10分钟完成。
- 零训练、无需微调，适合实时稀疏3D重建应用。
现有3D重建方法在密集多视角下表现优异，但在仅有少量视图时效果下降。尽管基于扩散模型的方法通过生成新视角增强数据，仍存在三大问题：（i）对已知视角边缘外的覆盖不足，（ii）生成视角间几何不一致，（iii）计算效率低。本文提出GaMO（Geometry-aware Multi-view Outpainter），将稀疏视图重建重构为多视角外推任务。不生成新视角，而是从现有相机位姿向外扩展视野，天然保持几何一致性并扩大场景覆盖。采用多视角条件与几何感知去噪策略，零样本无训练实现。在Replica、ScanNet++和Mip-NeRF 360数据集上的实验表明，该方法在3、6、9个输入视图下均表现优秀，整体运行时间控制在10分钟内，显著优于现有扩散方法。
原文摘要 · Abstract (English)
Recent 3D reconstruction methods achieve impressive results with dense multi-view imagery but struggle when only a few views are available. Various approaches, including regularization techniques, semantic priors, and geometric constraints, have been implemented to address this challenge. Recent diffusion-based approaches further improve performance by generating novel views to augment training data. Despite this progress, we identify three critical limitations in current state-of-the-art approaches: (i) inadequate coverage beyond known view peripheries, (ii) geometric inconsistencies across generated views, and (iii) computational inefficiency due to expensive pipelines. We introduce GaMO (Geometry-aware Multi-view Outpainter), a framework that reformulates sparse-view reconstruction through multi-view outpainting. Instead of generating new viewpoints, GaMO expands the field of view from existing camera poses, which inherently preserves geometric consistency while providing broader scene coverage. Our approach employs multi-view conditioning and geometry-aware denoising strategies in a zero-shot manner without training. Extensive experiments on Replica, ScanNet++, and Mip-NeRF 360 demonstrate strong reconstruction performance across sparse-view settings (3, 6, and 9 input views). Notably, our method is significantly more efficient than existing diffusion-based approaches, reducing the overall runtime to within 10 minutes. Project page: https://yichuanh.github.io/GaMO/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。