paper-with-me

홈 › Papers

Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization

2023-10-10 · Le Chen, Weirong Chen, Rui Wang, Marc Pollefeys

As a promising fashion for visual localization, scene coordinate regression (SCR) has seen tremendous progress in the past decade. Most recent methods usually adopt neural networks to learn the mapping from image pixels to 3D scene coordinates, which requires a vast amount of annotated training data. We propose to leverage Neural Radiance Fields (NeRF) to generate training samples for SCR. Despite NeRF's efficiency in rendering, many of the rendered data are polluted by artifacts or only contain minimal information gain, which can hinder the regression accuracy or bring unnecessary computational costs with redundant data. These challenges are addressed in three folds in this paper: (1) A NeRF is designed to separately predict uncertainties for the rendered color and depth images, which reveal data reliability at the pixel level. (2) SCR is formulated as deep evidential learning with epistemic uncertainty, which is used to evaluate information gain and scene coordinate quality. (3) Based on the three arts of uncertainties, a novel view selection policy is formed that significantly improves data efficiency. Experiments on public datasets demonstrate that our method could select the samples that bring the most information gain and promote the performance with the highest efficiency.

📄 PDF Abstract BibTeX arXiv:2310.06984

Code (0)

등록된 구현이 없습니다.

Tasks

NeRFregressionVisual Localization

Similar Papers 제목 키워드 기반

FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information

2023-11-29 · Wen Jiang, Boshu Lei, Kostas Daniilidis

This study addresses the challenging problem of active view selection and uncertainty quantification within the domain of Radiance Fields. Neural Radiance Fields (NeRF) have greatly advanced image rendering and reconstru…

NeRFUncertainty Quantification

These Magic Moments: Differentiable Uncertainty Quantification of Radiance Field Models

2025-03-18 · Parker Ewen, Hao Chen, Seth Isaacson, Joey Wilson 외

This paper introduces a novel approach to uncertainty quantification for radiance fields by leveraging higher-order moments of the rendering equation. Uncertainty quantification is crucial for downstream tasks including …

Decision MakingScene UnderstandingUncertainty Quantification

Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fields

2022-09-19 · Niko Sünderhauf, Jad Abou-Chakra, Dimity Miller

We show that ensembling effectively quantifies model uncertainty in Neural Radiance Fields (NeRFs) if a density-aware epistemic uncertainty term is considered. The naive ensembles investigated in prior work simply averag…

NeRFUncertainty Quantification

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

2024-09-04 · Jiaxin Guo, Jiangliu Wang, Ruofeng Wei, Di Kang 외

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, enha…

NeRFNeural RenderingNovel View Synthesis

Deformable Neural Radiance Fields using RGB and Event Cameras

2023-09-15 · ICCV 2023 1 · Qi Ma, Danda Pani Paudel, Ajad Chhatkuli, Luc van Gool

Modeling Neural Radiance Fields for fast-moving deformable objects from visual data alone is a challenging problem. A major issue arises due to the high deformation and low acquisition rates. To address this problem, we …