Self-supervised coarse-to-fine monocular depth estimation using a lightweight attention module

被引:0
|
作者
Yuanzhen Li
Fei Luo
Chunxia Xiao
机构
[1] Wuhan University,School of Computer Science
来源
Computational Visual Media | 2022年 / 8卷
关键词
monocular depth estimation; texture copy; depth drift; attention module;
D O I
暂无
中图分类号
学科分类号
摘要
Self-supervised monocular depth estimation has been widely investigated and applied in previous works. However, existing methods suffer from texture-copy, depth drift, and incomplete structure. It is difficult for normal CNN networks to completely understand the relationship between the object and its surrounding environment. Moreover, it is hard to design the depth smoothness loss to balance depth smoothness and sharpness. To address these issues, we propose a coarse-to-fine method with a normalized convolutional block attention module (NCBAM). In the coarse estimation stage, we incorporate the NCBAM into depth and pose networks to overcome the texture-copy and depth drift problems. Then, we use a new network to refine the coarse depth guided by the color image and produce a structure-preserving depth result in the refinement stage. Our method can produce results competitive with state-of-the-art methods. Comprehensive experiments prove the effectiveness of our two-stage method using the NCBAM.
引用
收藏
页码:631 / 647
页数:16
相关论文
共 50 条
  • [41] Self-Supervised Monocular Depth Estimation With Extensive Pretraining
    Choi, Hyukdoo
    IEEE ACCESS, 2021, 9 : 157236 - 157246
  • [42] Self-Supervised Monocular Depth Estimation with Extensive Pretraining
    Choi, Hyukdoo
    IEEE Access, 2021, 9 : 157236 - 157246
  • [43] MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Model
    Shao, Shuwei
    Pei, Zhongcai
    Chen, Weihai
    Sun, Dingchi
    Chen, Peter C. Y.
    Li, Zhengguo
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2025, 35 (04) : 3664 - 3678
  • [44] Self-Supervised Monocular Depth Estimation Using Hybrid Transformer Encoder
    Hwang, Seung-Jun
    Park, Sung-Jun
    Baek, Joong-Hwan
    Kim, Byungkyu
    IEEE SENSORS JOURNAL, 2022, 22 (19) : 18762 - 18770
  • [45] MDSNet: self-supervised monocular depth estimation for video sequences using self-attention and threshold mask
    Zhao, Jiaqi
    Zhao, Chaoyue
    Liu, Chunling
    Zhang, Chaojian
    Zhang, Wang
    JOURNAL OF ELECTRONIC IMAGING, 2022, 31 (05)
  • [46] Self-supervised monocular depth estimation via joint attention and intelligent mask loss
    Guo, Peng
    Pan, Shuguo
    Gao, Wang
    Khoshelham, Kourosh
    MACHINE VISION AND APPLICATIONS, 2025, 36 (01)
  • [47] Self-supervised monocular depth estimation with large kernel attention and dynamic scene perception
    Xiang, Xuezhi
    Wang, Yao
    Li, Xiaoheng
    Zhang, Lei
    Zhen, Xiantong
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2025, 108
  • [48] ATTENTION-BASED SELF-SUPERVISED LEARNING MONOCULAR DEPTH ESTIMATION WITH EDGE REFINEMENT
    Jiang, Chenweinan
    Liu, Haichun
    Li, Lanzhen
    Pan, Changchun
    2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 3218 - 3222
  • [49] Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation
    Zhang, Ning
    Nex, Francesco
    Vosselman, George
    Kerle, Norman
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 18537 - 18546
  • [50] LDA-Mono: A lightweight dual aggregation network for self-supervised monocular depth estimation
    Zhao, Bowen
    He, Hongdou
    Xu, Hang
    Shi, Peng
    Hao, Xiaobing
    Huang, Guoyan
    KNOWLEDGE-BASED SYSTEMS, 2024, 304