Depth Estimation Based on 3D Gaussian Splatting Siamese Defocus

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jinchang, Xu, Ningning, Zhang, Hao, Lu, Guoyu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908314314473472
author Zhang, Jinchang
Xu, Ningning
Zhang, Hao
Lu, Guoyu
author_facet Zhang, Jinchang
Xu, Ningning
Zhang, Hao
Lu, Guoyu
contents Depth estimation is a fundamental task in 3D geometry. While stereo depth estimation can be achieved through triangulation methods, it is not as straightforward for monocular methods, which require the integration of global and local information. The Depth from Defocus (DFD) method utilizes camera lens models and parameters to recover depth information from blurred images and has been proven to perform well. However, these methods rely on All-In-Focus (AIF) images for depth estimation, which is nearly impossible to obtain in real-world applications. To address this issue, we propose a self-supervised framework based on 3D Gaussian splatting and Siamese networks. By learning the blur levels at different focal distances of the same scene in the focal stack, the framework predicts the defocus map and Circle of Confusion (CoC) from a single defocused image, using the defocus map as input to DepthNet for monocular depth estimation. The 3D Gaussian splatting model renders defocused images using the predicted CoC, and the differences between these and the real defocused images provide additional supervision signals for the Siamese Defocus self-supervised network. This framework has been validated on both artificially synthesized and real blurred datasets. Subsequent quantitative and visualization experiments demonstrate that our proposed framework is highly effective as a DFD method.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12323
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Depth Estimation Based on 3D Gaussian Splatting Siamese Defocus
Zhang, Jinchang
Xu, Ningning
Zhang, Hao
Lu, Guoyu
Computer Vision and Pattern Recognition
Depth estimation is a fundamental task in 3D geometry. While stereo depth estimation can be achieved through triangulation methods, it is not as straightforward for monocular methods, which require the integration of global and local information. The Depth from Defocus (DFD) method utilizes camera lens models and parameters to recover depth information from blurred images and has been proven to perform well. However, these methods rely on All-In-Focus (AIF) images for depth estimation, which is nearly impossible to obtain in real-world applications. To address this issue, we propose a self-supervised framework based on 3D Gaussian splatting and Siamese networks. By learning the blur levels at different focal distances of the same scene in the focal stack, the framework predicts the defocus map and Circle of Confusion (CoC) from a single defocused image, using the defocus map as input to DepthNet for monocular depth estimation. The 3D Gaussian splatting model renders defocused images using the predicted CoC, and the differences between these and the real defocused images provide additional supervision signals for the Siamese Defocus self-supervised network. This framework has been validated on both artificially synthesized and real blurred datasets. Subsequent quantitative and visualization experiments demonstrate that our proposed framework is highly effective as a DFD method.
title Depth Estimation Based on 3D Gaussian Splatting Siamese Defocus
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.12323