用多层级采样和多视角一致性提升室内场景的细节重建质量
Fine-detailed Neural Indoor Scene Reconstruction using multi-level importance sampling and multi-view consistency
- 基于分割先验和分段指数权重，实现区域聚焦的射线采样
- 多视角特征与法向一致性监督使细节更清晰，重建更准确
- 相比已有方法在复杂室内场景中显著减少平滑误差
近期，神经隐式3D重建在室内场景中因简单高效而受到关注。以往方法虽能生成完整模型，但依赖单目法向或深度先验，易导致表面过度平滑且优化耗时。本文提出新方法FD-NeuS，通过多层级重要性采样与多视角一致性机制，学习精细的3D模型。具体地，利用分割先验引导区域级射线采样，并以分段指数函数作为沿射线采样的权重，强化对关键区域的关注；同时引入多视角特征一致性与多视角法向一致性作为监督信号与不确定性估计，进一步提升细节重建效果。大量定量与定性实验表明，FD-NeuS在多种场景下均优于现有方法。
原文摘要 · Abstract (English)
Recently, neural implicit 3D reconstruction in indoor scenarios has become popular due to its simplicity and impressive performance. Previous works could produce complete results leveraging monocular priors of normal or depth. However, they may suffer from over-smoothed reconstructions and long-time optimization due to unbiased sampling and inaccurate monocular priors. In this paper, we propose a novel neural implicit surface reconstruction method, named FD-NeuS, to learn fine-detailed 3D models using multi-level importance sampling strategy and multi-view consistency methodology. Specifically, we leverage segmentation priors to guide region-based ray sampling, and use piecewise exponential functions as weights to pilot 3D points sampling along the rays, ensuring more attention on important regions. In addition, we introduce multi-view feature consistency and multi-view normal consistency as supervision and uncertainty respectively, which further improve the reconstruction of details. Extensive quantitative and qualitative results show that FD-NeuS outperforms existing methods in various scenes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。