G4Splat：基于生成先验的几何引导高斯点云法
G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior
AI总结：
G4Splat通过几何引导的生成先验提升3D场景重建，有效解决多视角不一致性问题，实现高质量场景补全。
摘要：
尽管近年来利用预训练扩散模型的生成先验进行3D场景重建取得了进展，但现有方法仍面临两个关键限制。首先，由于缺乏可靠的几何监督，在已观测区域都难以产生高质量的重建，更不用说未观测区域了。其次，它们缺乏有效机制来减轻生成图像中的多视角不一致性，导致严重的形状-外观模糊性和降质的场景几何。在本文中，我们识别出准确的几何结构是有效利用生成模型提高3D场景重建的关键前提。我们首先提出利用平面结构的普遍性来推导准确的度量尺度深度图，在已观测和未观测区域提供可靠的监督。此外，我们将这种几何指导贯穿于生成管道中，以提高可见性掩膜估计，指导新视角选择，并在使用视频扩散模型进行补全时增强多视角一致性，从而实现准确且一致的场景补全。在Replica、ScanNet++、DeepBlending和Mip-NeRF 360上进行了广泛的实验，结果表明我们的方法在几何和外观重建上都优于现有基线，特别是在未观测区域。此外，我们的方法自然支持单视角输入和未置位视频，在室内外场景中具有强大的通用性，并具有实际应用价值。项目页面可在https://dali-jack.github.io/g4splat-web/上找到。
英文摘要：
Despite recent advances in leveraging generative prior from pre-trained diffusion models for 3D scene reconstruction, existing methods still face two critical limitations. First, due to the lack of reliable geometric supervision, they struggle to produce high-quality reconstructions even in observed regions, let alone in unobserved areas. Second, they lack effective mechanisms to mitigate multi-view inconsistencies in the generated images, leading to severe shape-appearance ambiguities and degraded scene geometry. In this paper, we identify accurate geometry as the fundamental prerequisite for effectively exploiting generative models to enhance 3D scene reconstruction. We first propose to leverage the prevalence of planar structures to derive accurate metric-scale depth maps, providing reliable supervision in both observed and unobserved regions. Furthermore, we incorporate this geometry guidance throughout the generative pipeline to improve visibility mask estimation, guide novel view selection, and enhance multi-view consistency when inpainting with video diffusion models, resulting in accurate and consistent scene completion. Extensive experiments on Replica, ScanNet++, DeepBlending and Mip-NeRF 360 show that our method consistently outperforms existing baselines in both geometry and appearance reconstruction, particularly for unobserved regions. Moreover, our method naturally supports single-view inputs and unposed videos, with strong generalizability in both indoor and outdoor scenarios with practical real-world applicability. The project page is available at https://dali-jack.github.io/g4splat-web/.
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。
