RoGSplat：从稀疏多视角图像学习鲁棒可泛化人体 Gaussian Splatting
RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images
AI总结：
提出 RoGSplat，利用 SMPL 先验点、像素/体素特征及深度引导的粗细 Gaussian 回归，实现稀疏视角下鲁棒可泛化的人体新视角合成。
摘要：
本文提出 RoGSplat，这是一种从稀疏多视角图像合成未见人物高保真新视角的新方法，且无需繁琐的逐对象优化。以往方法通常难以处理重叠很少的稀疏视角，并且在重建复杂人体几何方面效果较差；与之不同，所提方法能够在此类具有挑战性的条件下实现鲁棒重建。我们的核心思想是将 SMPL 顶点提升为稠密且可靠的三维先验点，以表示准确的人体几何，然后基于这些点回归人体 Gaussian 参数。为了解决 SMPL 模型与图像之间可能存在的未对齐问题，我们提出通过同时利用像素级特征和体素级特征来预测与图像对齐的三维先验点，并由此回归粗粒度 Gaussian。为增强捕捉高频细节的能力，我们进一步从粗粒度三维 Gaussian 渲染深度图，以帮助回归细粒度的逐像素 Gaussian。在多个基准数据集上的实验表明，我们的方法在新视角合成和跨数据集泛化方面均优于最先进方法。代码可在 https://github.com/iSEE-Laboratory/RoGSplat 获取。
英文摘要：
This paper presents RoGSplat, a novel approach for synthesizing high-fidelity novel views of unseen human from sparse multi-view images, while requiring no cumbersome per-subject optimization. Unlike previous methods that typically struggle with sparse views with few overlappings and are less effective in reconstructing complex human geometry, the proposed method enables robust reconstruction in such challenging conditions. Our key idea is to lift SMPL vertices to dense and reliable 3D prior points representing accurate human body geometry, and then regress human Gaussian parameters based on the points. To account for possible misalignment between SMPL model and images, we propose to predict image-aligned 3D prior points by leveraging both pixel-level features and voxel-level features, from which we regress the coarse Gaussians. To enhance the ability to capture high-frequency details, we further render depth maps from the coarse 3D Gaussians to help regress fine-grained pixel-wise Gaussians. Experiments on several benchmark datasets demonstrate that our method outperforms state-of-the-art methods in novel view synthesis and cross-dataset generalization. Our code is available at https://github.com/iSEE-Laboratory/RoGSplat.
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。
