Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation

被引:52
|
作者
Jung, Hyunyoung [1 ]
Park, Eunhyeok [2 ]
Yoo, Sungjoo [1 ]
机构
[1] Seoul Natl Univ, Seoul, South Korea
[2] POSTECH, Pohang, South Korea
关键词
D O I
10.1109/ICCV48922.2021.01241
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Self-supervised monocular depth estimation has been widely studied, owing to its practical importance and recent promising improvements. However, most works suffer from limited supervision of photometric consistency, especially in weak texture regions and at object boundaries. To overcome this weakness, we propose novel ideas to improve self-supervised monocular depth estimation by leveraging cross-domain information, especially scene semantics. We focus on incorporating implicit semantic knowledge into geometric representation enhancement and suggest two ideas: a metric learning approach that exploits the semantics-guided local geometry to optimize intermediate depth representations and a novel feature fusion module that judiciously utilizes cross-modality between two heterogeneous feature representations. We comprehensively evaluate our methods on the KITTI dataset and demonstrate that our method outperforms state-of-the-art methods. The source code is available at https://github.com/hyBlue/FSRE-Depth.
引用
收藏
页码:12622 / 12632
页数:11
相关论文
共 50 条
  • [41] Image Masking for Robust Self-Supervised Monocular Depth Estimation
    Chawla, Hemang
    Jeeveswaran, Kishaan
    Arani, Elahe
    Zonooz, Bahram
    [J]. 2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023), 2023, : 10054 - 10060
  • [42] Exploring the vulnerability of self-supervised monocular depth estimation models
    Hou, Ruitao
    Mo, Kanghua
    Long, Yucheng
    Li, Ning
    Rao, Yuan
    [J]. INFORMATION SCIENCES, 2024, 677
  • [43] Self-Supervised Monocular Depth Estimation by Digging into Uncertainty Quantification
    Yuan-Zhen Li
    Sheng-Jie Zheng
    Zi-Xin Tan
    Tuo Cao
    Fei Luo
    Chun-Xia Xiao
    [J]. Journal of Computer Science and Technology, 2023, 38 : 510 - 525
  • [44] Graph semantic information for self-supervised monocular depth estimation
    Zhang, Dongdong
    Wang, Chunping
    Wang, Huiying
    Fu, Qiang
    [J]. PATTERN RECOGNITION, 2024, 156
  • [45] Self-supervised Monocular Depth Estimation on Unseen Synthetic Cameras
    Diana-Albelda, Cecilia
    Bravo Perez-Villar, Juan Ignacio
    Montalvo, Javier
    Garcia-Martin, Alvaro
    Bescos Cano, Jesus
    [J]. PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, CIARP 2023, PT I, 2024, 14469 : 449 - 463
  • [46] MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer
    Zhao, Chaoqiang
    Zhang, Youmin
    Poggi, Matteo
    Tosi, Fabio
    Guo, Xianda
    Zhu, Zheng
    Huang, Guan
    Tang, Yang
    Mattoccia, Stefano
    [J]. 2022 INTERNATIONAL CONFERENCE ON 3D VISION, 3DV, 2022, : 668 - 678
  • [47] Self-Supervised Deep Monocular Depth Estimation With Ambiguity Boosting
    Bello, Juan Luis Gonzalez
    Kim, Munchurl
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (12) : 9131 - 9149
  • [48] Self-Supervised Human Depth Estimation from Monocular Videos
    Tan, Feitong
    Zhu, Hao
    Cui, Zhaopeng
    Zhu, Siyu
    Pollefeys, Marc
    Tan, Ping
    [J]. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 647 - 656
  • [49] Self-Supervised Monocular Depth Estimation with Multi-constraints
    Yang, Xinpeng
    Zhang, Sen
    Zhao, Baoyong
    [J]. 2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 8422 - 8427
  • [50] Self-Supervised Monocular Depth Estimation Based on Channel Attention
    Tao, Bo
    Chen, Xinbo
    Tong, Xiliang
    Jiang, Du
    Chen, Baojia
    [J]. PHOTONICS, 2022, 9 (06)