SN ^ eRF: A Framework for Neural Radiance Fields given Sparse and Noisy Poses

Neural Radiance Fields (NeRFs) have shown impressive capabilities in synthesizing photorealistic novel views. However, their application to room-size scenes is limited by the requirement of several hundred views with accurate poses for training. To address this challenge, we propose SN ^{2} eRF, a f...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on visualization and computer graphics 2024-08, p.1-12
Main Authors: Chen, Hao-Xiang, Li, Jiayi, Mu, Tai-Jiang, Hu, Shi-Min
Format: Article
Language:English
Subjects:
Accuracy
Cameras
Few View Training
Geometry
Neural radiance field
Neural Radiance Fields
Noise measurement
Optimization
Pose Refinement
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural Radiance Fields (NeRFs) have shown impressive capabilities in synthesizing photorealistic novel views. However, their application to room-size scenes is limited by the requirement of several hundred views with accurate poses for training. To address this challenge, we propose SN ^{2} eRF, a framework which can reconstruct the neural radiance field with significantly fewer views and noisy poses by exploiting multiple priors. Our key insight is to leverage both multi-view and monocular priors to constrain the optimization of NeRF in the setting of sparse and noisy pose inputs. Specifically, we extract and match key points to constrain pose optimization and use Ray Transformer with a monocular depth estimator to provide dense depth prior for geometry optimization. Benefiting from these priors, our approach achieves state-of-the-art accuracy in novel view synthesis for indoor room scenarios.
ISSN:1077-2626
1941-0506
DOI:10.1109/TVCG.2024.3439583