研究人员推出了一种新颖的几何约束方法 VisDom，用于稀疏新视图合成，可从有限的输入图像中提高 3D 重建质量。这种无需学习的方法通过强制执行最低多视图可见性要求，有效过滤模糊几何，从而增强了现有的 NeRF 和 Gaussian Splatting 管道。VisDom 在各种数据集上均表现出持续的改进，能够仅用四张图像即可实现高质量的对象重建，并降低了训练成本。 AI
影响 提高了从有限数据进行 3D 重建的质量，可能减少了对广泛采集设置的需求。
排序理由 该集群包含一篇详细介绍计算机视觉新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.20531v1 Announce Type: new Abstract: Sparse novel view synthesis (NVS) remains challenging due to the ambiguity of recovering 3D geometry from few input views. While NeRF- and Gaussian Splatting (GS)-based methods perform well with dense supervision, they often overfit…
Sparse novel view synthesis (NVS) remains challenging due to the ambiguity of recovering 3D geometry from few input views. While NeRF- and Gaussian Splatting (GS)-based methods perform well with dense supervision, they often overfit in sparse settings, producing floating artifact…