VidSplat：基于几何引导视频扩散先验的高斯点云重建
VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors
AI总结：
VidSplat通过几何引导的视频扩散先验，解决稀疏视图下3D场景重建问题，提出免训练生成框架，迭代合成新视角以恢复完整3D场景。
摘要：
高斯点云在多视图表面重建中取得显著进展，但在视图不足时表现出明显退化。尽管近期工作通过增强多视图一致性生成合理表面，但仍难以推断未观测、遮挡或弱约束区域。为此，我们提出VidSplat，一种免训练生成重建框架，利用强大视频扩散先验迭代合成新视角以补充缺失输入覆盖，从而从稀疏输入中恢复完整3D场景。具体而言，我们解决两个关键挑战，使生成与重建有效整合。首先，针对3D一致生成，我们提出一种免训练、分阶段去噪策略，通过渲染的RGB和掩码图像适配地引导去噪方向向底层几何。其次，为增强重建，我们开发一种迭代机制，采样相机轨迹、探索未观测区域、合成新视角并通过置信度加权细化补充训练。VidSplat对稀疏输入乃至单张图像均表现稳健。在广泛使用的基准测试中，我们的方法在稀疏视图场景重建中表现出优越性能。
英文摘要：
Gaussian Splatting has achieved remarkable progress in multi-view surface reconstruction, yet it exhibits notable degradation when only few views are available. Although recent efforts alleviate this issue by enhancing multi-view consistency to produce plausible surfaces, they struggle to infer unseen, occluded, or weakly constrained regions beyond the input coverage. To address this limitation, we present VidSplat, a training-free generative reconstruction framework that leverages powerful video diffusion priors to iteratively synthesize novel views that compensate for missing input coverage, and thereby recover complete 3D scenes from sparse inputs. Specifically, we tackle two key challenges that enable the effective integration of generation and reconstruction. First, for 3D consistent generation, we elaborate a training-free, stage-wise denoising strategy that adaptively guides the denoising direction toward the underlying geometry using the rendered RGB and mask images. Second, to enhance the reconstruction, we develop an iterative mechanism that samples camera trajectories, explores unobserved regions, synthesizes novel views, and supplements training through confidence weighted refinement. VidSplat performs robustly to sparse input and even a single image. Extensive experiments on widely used benchmarks demonstrate our superior performance in sparse-view scene reconstruction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
