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
  • [21] Self-supervised monocular depth estimation with direct methods
    Wang, Haixia
    Sun, Yehao
    Wu, Q. M. Jonathan
    Lu, Xiao
    Wang, Xiuling
    Zhang, Zhiguo
    [J]. NEUROCOMPUTING, 2021, 421 : 340 - 348
  • [22] Learn to Adapt for Self-Supervised Monocular Depth Estimation
    Sun, Qiyu
    Yen, Gary G. G.
    Tang, Yang
    Zhao, Chaoqiang
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 35 (11) : 1 - 13
  • [23] Self-Supervised Monocular Depth Estimation With Multiscale Perception
    Zhang, Yourun
    Gong, Maoguo
    Li, Jianzhao
    Zhang, Mingyang
    Jiang, Fenlong
    Zhao, Hongyu
    [J]. IEEE Transactions on Image Processing, 2022, 31 : 3251 - 3266
  • [24] Self-Supervised Monocular Depth Estimation With Multiscale Perception
    Zhang, Yourun
    Gong, Maoguo
    Li, Jianzhao
    Zhang, Mingyang
    Jiang, Fenlong
    Zhao, Hongyu
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 3251 - 3266
  • [25] Self-supervised learning for fine-grained monocular 3D face reconstruction in the wild
    Huang, Dongjin
    Shi, Yongsheng
    Liu, Jinhua
    Tang, Wen
    [J]. MULTIMEDIA SYSTEMS, 2024, 30 (04)
  • [26] Self-Supervised Monocular Depth Estimation with Extensive Pretraining
    Choi, Hyukdoo
    [J]. IEEE Access, 2021, 9 : 157236 - 157246
  • [27] Self-Supervised Monocular Depth Estimation With Extensive Pretraining
    Choi, Hyukdoo
    [J]. IEEE ACCESS, 2021, 9 : 157236 - 157246
  • [28] Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network
    Han, Wencheng
    Yin, Junbo
    Shen, Jianbing
    [J]. 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 8579 - 8589
  • [29] RENA-Depth: toward recursion representation enhancement in neighborhood attention guided lightweight self-supervised monocular depth estimation
    Yang, Chaochao
    Lu, Yuanyao
    Qiu, Yongsheng
    Wang, Yuantao
    [J]. OPTICAL ENGINEERING, 2024, 63 (08)
  • [30] Learning Effective Geometry Representation from Videos for Self-Supervised Monocular Depth Estimation
    Zhao, Hailiang
    Kong, Yongyi
    Zhang, Chonghao
    Zhang, Haoji
    Zhao, Jiansen
    [J]. ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2024, 13 (06)