Exploiting Deblurring Networks for Radiance Fields

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Choi, Haeyun, Yang, Heemin, Han, Janghyeok, Cho, Sunghyun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909548999081984
author Choi, Haeyun
Yang, Heemin
Han, Janghyeok
Cho, Sunghyun
author_facet Choi, Haeyun
Yang, Heemin
Han, Janghyeok
Cho, Sunghyun
contents In this paper, we propose DeepDeblurRF, a novel radiance field deblurring approach that can synthesize high-quality novel views from blurred training views with significantly reduced training time. DeepDeblurRF leverages deep neural network (DNN)-based deblurring modules to enjoy their deblurring performance and computational efficiency. To effectively combine DNN-based deblurring and radiance field construction, we propose a novel radiance field (RF)-guided deblurring and an iterative framework that performs RF-guided deblurring and radiance field construction in an alternating manner. Moreover, DeepDeblurRF is compatible with various scene representations, such as voxel grids and 3D Gaussians, expanding its applicability. We also present BlurRF-Synth, the first large-scale synthetic dataset for training radiance field deblurring frameworks. We conduct extensive experiments on both camera motion blur and defocus blur, demonstrating that DeepDeblurRF achieves state-of-the-art novel-view synthesis quality with significantly reduced training time.
format Preprint
id arxiv_https___arxiv_org_abs_2502_14454
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploiting Deblurring Networks for Radiance Fields
Choi, Haeyun
Yang, Heemin
Han, Janghyeok
Cho, Sunghyun
Computer Vision and Pattern Recognition
In this paper, we propose DeepDeblurRF, a novel radiance field deblurring approach that can synthesize high-quality novel views from blurred training views with significantly reduced training time. DeepDeblurRF leverages deep neural network (DNN)-based deblurring modules to enjoy their deblurring performance and computational efficiency. To effectively combine DNN-based deblurring and radiance field construction, we propose a novel radiance field (RF)-guided deblurring and an iterative framework that performs RF-guided deblurring and radiance field construction in an alternating manner. Moreover, DeepDeblurRF is compatible with various scene representations, such as voxel grids and 3D Gaussians, expanding its applicability. We also present BlurRF-Synth, the first large-scale synthetic dataset for training radiance field deblurring frameworks. We conduct extensive experiments on both camera motion blur and defocus blur, demonstrating that DeepDeblurRF achieves state-of-the-art novel-view synthesis quality with significantly reduced training time.
title Exploiting Deblurring Networks for Radiance Fields
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.14454