BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes
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/.
Code (0)
등록된 구현이 없습니다.
Tasks
NeRFSimilar Papers 제목 키워드 기반
FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models
Recent works on generalizable NeRFs have shown promising results on novel view synthesis from single or few images. However, such models have rarely been applied on other downstream tasks beyond synthesis such as semanti…
NeRFNeural RenderingNovel View SynthesisGen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design
Novel view synthesis is an essential functionality for enabling immersive experiences in various Augmented- and Virtual-Reality (AR/VR) applications, for which generalizable Neural Radiance Fields (NeRFs) have gained inc…
Generalizable Novel View SynthesisNeRFNovel View SynthesisActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs
While NeRF-based human representations have shown impressive novel view synthesis results, most methods still rely on a large number of images / views for training. In this work, we propose a novel animatable NeRF called…
NeRFNovel View SynthesisAdvancing Adversarial Robustness in GNeRFs: The IL2-NeRF Attack
Generalizable Neural Radiance Fields (GNeRF) are recognized as one of the most promising techniques for novel view synthesis and 3D model generation in real-world applications. However, like other generative models i…
3D ReconstructionAdversarial AttackAdversarial RobustnessNeRF+1MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose
We propose a generalizable neural radiance fields - MonoNeRF, that can be trained on large-scale monocular videos of moving in static scenes without any ground-truth annotations of depth and camera poses. MonoNeRF follow…
Camera Pose EstimationDecoderDepth EstimationDisentanglement+3