BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes

TL;DR

BoostMVSNeRFs enhances the rendering quality of MVS-based NeRFs in large-scale scenes by selecting and combining multiple cost volumes, without requiring training, thus improving quality and adaptability in outdoor scenarios.

Contribution

The paper introduces BoostMVSNeRFs, a novel method that improves MVS-based NeRFs' quality in large-scale scenes by combining multiple cost volumes without training.

Findings

Significant quality improvements in large-scale scene rendering.

Effective in outdoor unbounded scenarios.

No additional training required for the method.

Abstract

While Neural Radiance Fields (NeRFs) have demonstrated exceptional quality, their protracted training duration remains a limitation. Generalizable and MVS-based NeRFs, although capable of mitigating training time, often incur tradeoffs in quality. This paper presents a novel approach called BoostMVSNeRFs to enhance the rendering quality of MVS-based NeRFs in large-scale scenes. We first identify limitations in MVS-based NeRF methods, such as restricted viewport coverage and artifacts due to limited input views. Then, we address these limitations by proposing a new method that selects and combines multiple cost volumes during volume rendering. Our method does not require training and can adapt to any MVS-based NeRF methods in a feed-forward fashion to improve rendering quality. Furthermore, our approach is also end-to-end trainable, allowing fine-tuning on specific scenes. We demonstrate the effectiveness of our method through experiments on large-scale datasets, showing significant rendering quality improvements in large-scale scenes and unbounded outdoor scenarios. We release the source code of BoostMVSNeRFs at https://su-terry.github.io/BoostMVSNeRFs/.