期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
卷 32, 期 4, 页码 1751-1766出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2021.3080928
关键词
Estimation; Cameras; Semantics; Training; Three-dimensional displays; Deep learning; Geometry; Depth map estimation; self-supervised learning; quadtree constraint; feature fusion
资金
- National Natural Science Foundation of China [61802253, 61772328, 61831018, U2033218]
- National Key Research and Development Project of Ministry of Science and Technology of China [2020AAA0109302, 2020AAA0109300]
- Chenguang Talented Program of Shanghai [17CG59]
In this paper, a novel self-supervised depth estimation network is proposed, which utilizes a quadtree constraint to optimize the depth estimation network. Photometric loss and depth loss based on quadtree are introduced to address the issue of multiple depth values in repeated structures and uniform texture regions. Experimental results demonstrate that the proposed method outperforms state-of-the-art approaches for depth estimation.
Depth estimation from a camera is an important task for 3D perception. Recently, without using the labeled ground truth of depth map, a self-supervised deep learning network can use relative pose to synthesize the target image from the reference image, and the photometric error between synthesized reference image and real one is used as self-supervisory signal. In this paper, we propose a novel self-supervised depth estimation network, which takes advantage of the quadtree constraint to optimize the depth estimation network. Based on the quadtree constraint, the photometric loss and depth loss of quadtree are proposed. In order to solve the problem that multiple depth values in repeated structures and uniform texture regions can cause relatively low photometric loss, we use quadtree-based photometric loss, which calculates the averaged photometric loss in quadtree blocks instead of the pixel-wise loss. For the problem of imbalanced depth distribution, we use quadtree depth loss, which constrains the depth inconsistency within quadtree blocks. The depth estimation network is composed of deep fusion module and cross-layer feature fusion module, which can better extract the feature information of RGB image and sparse keypoints depths, and makes full use of the detail information of the shallow feature map and the semantic information of the deep feature map to enrich the feature information extraction. Experimental results demonstrate that our method outperforms the state-of-the-art approaches of depth estimation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据