UC-NeRF: Uncertainty-aware Conditional Neural Radiance Fields from Endoscopic Sparse Views

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Jiaxin, Wang, Jiangliu, Wei, Ruofeng, Kang, Di, Dou, Qi, Liu, Yun-hui
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929585277370368
author Guo, Jiaxin
Wang, Jiangliu
Wei, Ruofeng
Kang, Di
Dou, Qi
Liu, Yun-hui
author_facet Guo, Jiaxin
Wang, Jiangliu
Wei, Ruofeng
Kang, Di
Dou, Qi
Liu, Yun-hui
contents Visualizing surgical scenes is crucial for revealing internal anatomical structures during minimally invasive procedures. Novel View Synthesis is a vital technique that offers geometry and appearance reconstruction, enhancing understanding, planning, and decision-making in surgical scenes. Despite the impressive achievements of Neural Radiance Field (NeRF), its direct application to surgical scenes produces unsatisfying results due to two challenges: endoscopic sparse views and significant photometric inconsistencies. In this paper, we propose uncertainty-aware conditional NeRF for novel view synthesis to tackle the severe shape-radiance ambiguity from sparse surgical views. The core of UC-NeRF is to incorporate the multi-view uncertainty estimation to condition the neural radiance field for modeling the severe photometric inconsistencies adaptively. Specifically, our UC-NeRF first builds a consistency learner in the form of multi-view stereo network, to establish the geometric correspondence from sparse views and generate uncertainty estimation and feature priors. In neural rendering, we design a base-adaptive NeRF network to exploit the uncertainty estimation for explicitly handling the photometric inconsistencies. Furthermore, an uncertainty-guided geometry distillation is employed to enhance geometry learning. Experiments on the SCARED and Hamlyn datasets demonstrate our superior performance in rendering appearance and geometry, consistently outperforming the current state-of-the-art approaches. Our code will be released at https://github.com/wrld/UC-NeRF.
format Preprint
id arxiv_https___arxiv_org_abs_2409_02917
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle UC-NeRF: Uncertainty-aware Conditional Neural Radiance Fields from Endoscopic Sparse Views
Guo, Jiaxin
Wang, Jiangliu
Wei, Ruofeng
Kang, Di
Dou, Qi
Liu, Yun-hui
Computer Vision and Pattern Recognition
Artificial Intelligence
Visualizing surgical scenes is crucial for revealing internal anatomical structures during minimally invasive procedures. Novel View Synthesis is a vital technique that offers geometry and appearance reconstruction, enhancing understanding, planning, and decision-making in surgical scenes. Despite the impressive achievements of Neural Radiance Field (NeRF), its direct application to surgical scenes produces unsatisfying results due to two challenges: endoscopic sparse views and significant photometric inconsistencies. In this paper, we propose uncertainty-aware conditional NeRF for novel view synthesis to tackle the severe shape-radiance ambiguity from sparse surgical views. The core of UC-NeRF is to incorporate the multi-view uncertainty estimation to condition the neural radiance field for modeling the severe photometric inconsistencies adaptively. Specifically, our UC-NeRF first builds a consistency learner in the form of multi-view stereo network, to establish the geometric correspondence from sparse views and generate uncertainty estimation and feature priors. In neural rendering, we design a base-adaptive NeRF network to exploit the uncertainty estimation for explicitly handling the photometric inconsistencies. Furthermore, an uncertainty-guided geometry distillation is employed to enhance geometry learning. Experiments on the SCARED and Hamlyn datasets demonstrate our superior performance in rendering appearance and geometry, consistently outperforming the current state-of-the-art approaches. Our code will be released at https://github.com/wrld/UC-NeRF.
title UC-NeRF: Uncertainty-aware Conditional Neural Radiance Fields from Endoscopic Sparse Views
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2409.02917