Bayesian Monocular Depth Refinement via Neural Radiance Fields

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Muthukkumar, Arun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912946107449344
author Muthukkumar, Arun
author_facet Muthukkumar, Arun
contents Monocular depth estimation has applications in many fields, such as autonomous navigation and extended reality, making it an essential computer vision task. However, current methods often produce smooth depth maps that lack the fine geometric detail needed for accurate scene understanding. We propose MDENeRF, an iterative framework that refines monocular depth estimates using depth information from Neural Radiance Fields (NeRFs). MDENeRF consists of three components: (1) an initial monocular estimate for global structure, (2) a NeRF trained on perturbed viewpoints, with per-pixel uncertainty, and (3) Bayesian fusion of the noisy monocular and NeRF depths. We derive NeRF uncertainty from the volume rendering process to iteratively inject high-frequency fine details. Meanwhile, our monocular prior maintains global structure. We demonstrate improvements on key metrics and experiments using indoor scenes from the SUN RGB-D dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03869
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bayesian Monocular Depth Refinement via Neural Radiance Fields
Muthukkumar, Arun
Computer Vision and Pattern Recognition
Graphics
Machine Learning
Robotics
Monocular depth estimation has applications in many fields, such as autonomous navigation and extended reality, making it an essential computer vision task. However, current methods often produce smooth depth maps that lack the fine geometric detail needed for accurate scene understanding. We propose MDENeRF, an iterative framework that refines monocular depth estimates using depth information from Neural Radiance Fields (NeRFs). MDENeRF consists of three components: (1) an initial monocular estimate for global structure, (2) a NeRF trained on perturbed viewpoints, with per-pixel uncertainty, and (3) Bayesian fusion of the noisy monocular and NeRF depths. We derive NeRF uncertainty from the volume rendering process to iteratively inject high-frequency fine details. Meanwhile, our monocular prior maintains global structure. We demonstrate improvements on key metrics and experiments using indoor scenes from the SUN RGB-D dataset.
title Bayesian Monocular Depth Refinement via Neural Radiance Fields
topic Computer Vision and Pattern Recognition
Graphics
Machine Learning
Robotics
url https://arxiv.org/abs/2601.03869