Improving Neural Radiance Fields with Depth-aware Optimization for Novel View Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Shu, Li, Junyao, Zhang, Yang, Zou, Beiji
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911779834036224
author Chen, Shu
Li, Junyao
Zhang, Yang
Zou, Beiji
author_facet Chen, Shu
Li, Junyao
Zhang, Yang
Zou, Beiji
contents With dense inputs, Neural Radiance Fields (NeRF) is able to render photo-realistic novel views under static conditions. Although the synthesis quality is excellent, existing NeRF-based methods fail to obtain moderate three-dimensional (3D) structures. The novel view synthesis quality drops dramatically given sparse input due to the implicitly reconstructed inaccurate 3D-scene structure. We propose SfMNeRF, a method to better synthesize novel views as well as reconstruct the 3D-scene geometry. SfMNeRF leverages the knowledge from the self-supervised depth estimation methods to constrain the 3D-scene geometry during view synthesis training. Specifically, SfMNeRF employs the epipolar, photometric consistency, depth smoothness, and position-of-matches constraints to explicitly reconstruct the 3D-scene structure. Through these explicit constraints and the implicit constraint from NeRF, our method improves the view synthesis as well as the 3D-scene geometry performance of NeRF at the same time. In addition, SfMNeRF synthesizes novel sub-pixels in which the ground truth is obtained by image interpolation. This strategy enables SfMNeRF to include more samples to improve generalization performance. Experiments on two public datasets demonstrate that SfMNeRF surpasses state-of-the-art approaches. Code is available at https://github.com/XTU-PR-LAB/SfMNeRF
format Preprint
id arxiv_https___arxiv_org_abs_2304_05218
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improving Neural Radiance Fields with Depth-aware Optimization for Novel View Synthesis
Chen, Shu
Li, Junyao
Zhang, Yang
Zou, Beiji
Computer Vision and Pattern Recognition
With dense inputs, Neural Radiance Fields (NeRF) is able to render photo-realistic novel views under static conditions. Although the synthesis quality is excellent, existing NeRF-based methods fail to obtain moderate three-dimensional (3D) structures. The novel view synthesis quality drops dramatically given sparse input due to the implicitly reconstructed inaccurate 3D-scene structure. We propose SfMNeRF, a method to better synthesize novel views as well as reconstruct the 3D-scene geometry. SfMNeRF leverages the knowledge from the self-supervised depth estimation methods to constrain the 3D-scene geometry during view synthesis training. Specifically, SfMNeRF employs the epipolar, photometric consistency, depth smoothness, and position-of-matches constraints to explicitly reconstruct the 3D-scene structure. Through these explicit constraints and the implicit constraint from NeRF, our method improves the view synthesis as well as the 3D-scene geometry performance of NeRF at the same time. In addition, SfMNeRF synthesizes novel sub-pixels in which the ground truth is obtained by image interpolation. This strategy enables SfMNeRF to include more samples to improve generalization performance. Experiments on two public datasets demonstrate that SfMNeRF surpasses state-of-the-art approaches. Code is available at https://github.com/XTU-PR-LAB/SfMNeRF
title Improving Neural Radiance Fields with Depth-aware Optimization for Novel View Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2304.05218