Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Prior

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Byeonghyeon, Lee, Howoong, Ali, Usman, Park, Eunbyung
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910285297614848
author Lee, Byeonghyeon
Lee, Howoong
Ali, Usman
Park, Eunbyung
author_facet Lee, Byeonghyeon
Lee, Howoong
Ali, Usman
Park, Eunbyung
contents Neural Radiance Fields (NeRF) have shown remarkable performance in neural rendering-based novel view synthesis. However, NeRF suffers from severe visual quality degradation when the input images have been captured under imperfect conditions, such as poor illumination, defocus blurring, and lens aberrations. Especially, defocus blur is quite common in the images when they are normally captured using cameras. Although few recent studies have proposed to render sharp images of considerably high-quality, yet they still face many key challenges. In particular, those methods have employed a Multi-Layer Perceptron (MLP) based NeRF, which requires tremendous computational time. To overcome these shortcomings, this paper proposes a novel technique Sharp-NeRF -- a grid-based NeRF that renders clean and sharp images from the input blurry images within half an hour of training. To do so, we used several grid-based kernels to accurately model the sharpness/blurriness of the scene. The sharpness level of the pixels is computed to learn the spatially varying blur kernels. We have conducted experiments on the benchmarks consisting of blurry images and have evaluated full-reference and non-reference metrics. The qualitative and quantitative results have revealed that our approach renders the sharp novel views with vivid colors and fine details, and it has considerably faster training time than the previous works. Our project page is available at https://benhenryl.github.io/SharpNeRF/
format Preprint
id arxiv_https___arxiv_org_abs_2401_00825
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Prior
Lee, Byeonghyeon
Lee, Howoong
Ali, Usman
Park, Eunbyung
Computer Vision and Pattern Recognition
Graphics
Image and Video Processing
Neural Radiance Fields (NeRF) have shown remarkable performance in neural rendering-based novel view synthesis. However, NeRF suffers from severe visual quality degradation when the input images have been captured under imperfect conditions, such as poor illumination, defocus blurring, and lens aberrations. Especially, defocus blur is quite common in the images when they are normally captured using cameras. Although few recent studies have proposed to render sharp images of considerably high-quality, yet they still face many key challenges. In particular, those methods have employed a Multi-Layer Perceptron (MLP) based NeRF, which requires tremendous computational time. To overcome these shortcomings, this paper proposes a novel technique Sharp-NeRF -- a grid-based NeRF that renders clean and sharp images from the input blurry images within half an hour of training. To do so, we used several grid-based kernels to accurately model the sharpness/blurriness of the scene. The sharpness level of the pixels is computed to learn the spatially varying blur kernels. We have conducted experiments on the benchmarks consisting of blurry images and have evaluated full-reference and non-reference metrics. The qualitative and quantitative results have revealed that our approach renders the sharp novel views with vivid colors and fine details, and it has considerably faster training time than the previous works. Our project page is available at https://benhenryl.github.io/SharpNeRF/
title Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Prior
topic Computer Vision and Pattern Recognition
Graphics
Image and Video Processing
url https://arxiv.org/abs/2401.00825