We represent the ResNeRF, a novel geometry-guided two-stage framework for indoor scene novel view synthesis. Be aware of that a good geometry would greatly boost the performance of novel view synthesis, and to avoid the geometry ambiguity issue, we propose to characterize the density distribution of the scene based on a base density estimated from scene geometry and a residual density parameterized by the geometry. In the first stage, we focus on geometry reconstruction based on SDF representation, which would lead to a good geometry surface of the scene and also a sharp density. In the second stage, the residual density is learned based on the SDF learned in the first stage for encoding more details about the appearance. In this way, our method can better learn the density distribution with the geometry prior for high-fidelity novel view synthesis while preserving the 3D structures. Experiments on large-scale indoor scenes with many less-observed and textureless areas show that with the good 3D surface, our method achieves state-of-the-art performance for novel view synthesis.

翻译：我们提出了ResNeRF，一种新颖的几何引导两阶段框架，用于室内场景新视角合成。鉴于良好的几何结构能显著提升新视角合成性能，同时为避免几何模糊性问题，我们建议基于场景几何估计的基密度与由几何参数化的残差密度来表征场景的密度分布。在第一阶段，我们专注于基于有符号距离函数（SDF）表示的几何重建，这能获得良好的场景几何表面和锐利的密度。在第二阶段，基于第一阶段习得的SDF学习残差密度，以编码更多外观细节。通过这种方式，我们的方法能更好地利用几何先验学习密度分布，在保持3D结构的同时实现高保真新视角合成。在包含大量稀疏观测及无纹理区域的大规模室内场景上的实验表明，凭借良好的3D表面，我们的方法在新视角合成任务上达到了最优性能。