BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes
This work addresses quality limitations in fast, generalizable NeRF methods for large-scale scene synthesis, offering an incremental improvement over existing MVS-based approaches.
The paper tackles the problem of low rendering quality in generalizable, multi-view stereo (MVS)-based Neural Radiance Fields (NeRFs) for large-scale scenes, and proposes BoostMVSNeRFs, a method that selects and combines multiple cost volumes to significantly improve quality without requiring training.
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/.