ADAPTIVE WEIGHTED NETWORK WITH EDGE ENHANCEMENT MODULE FOR MONOCULAR SELF-SUPERVISED DEPTH ESTIMATION

被引:1
|
作者
Liu, Hong [1 ]
Zhu, Ying [1 ]
Hua, Guoliang [1 ]
Huang, Weibo [1 ]
Ding, Runwei [1 ]
机构
[1] Peking Univ, Shenzhen Grad Sch, Key Lab Machine Percept, Beijing, Peoples R China
来源
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2022年
基金
中国国家自然科学基金;
关键词
Monocular self-supervised depth estimation; Edge enhancement module; Texture sparsity based adaptive weighted loss;
D O I
10.1109/ICASSP43922.2022.9746689
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Monocular self-supervised depth estimation can be easily applied in many areas since only a single camera is required. However, current methods do not predict well in depth borders. Besides, factors such as occlusion and texture sparsity can lead to the failure of the photometric consistency, affecting the prediction performance. To overcome these deficiencies, an adaptive weighted monocular self-supervised depth estimation framework that exploits enhanced edge information and texture sparsity based adaptive weights is proposed. In particular, a module named edge enhancement module (EEM) is designed to be embedded into the current depth prediction network to extract edge details for clearer depth prediction in depth borders. Moreover, a texture sparsity based adaptive weighted (TSAW) loss is introduced to assign different weights according to texture sparsity, enabling a more targeted construction of geometric constraints. Experimental results on the KITTI dataset demonstrate that the proposed network outperforms state-of-the-art methods.
引用
收藏
页码:2340 / 2344
页数:5
相关论文
共 50 条
  • [31] Self-Supervised Monocular Depth Estimation With Positional Shift Depth Variance and Adaptive Disparity Quantization
    Bello, Juan Luis Gonzalez
    Moon, Jaeho
    Kim, Munchurl
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 2074 - 2089
  • [32] Edge Devices Friendly Self-Supervised Monocular Depth Estimation via Knowledge Distillation
    Gao, Wei
    Rao, Di
    Yang, Yang
    Chen, Jie
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (12) : 8470 - 8477
  • [33] 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
  • [34] HPD-Depth: High performance decoding network for self-supervised monocular depth estimation
    Wu, Liehao
    Wang, Laihua
    Wei, Guanghui
    Yu, Yang
    IMAGE AND VISION COMPUTING, 2025, 154
  • [35] Self-Supervised Monocular Depth Estimation From Videos via Adaptive Reconstruction Constraints
    Ye, Xinchen
    Ou, Yuxiang
    Wu, Biao
    Xu, Rui
    Li, Haojie
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2025, 35 (03) : 2161 - 2172
  • [36] Self-supervised coarse-to-fine monocular depth estimation using a lightweight attention module
    Yuanzhen Li
    Fei Luo
    Chunxia Xiao
    Computational Visual Media, 2022, 8 : 631 - 647
  • [37] Self-Supervised Monocular Depth Estimation With 3-D Displacement Module for Laparoscopic Images
    Xu, Chi
    Huang, Baoru
    Elson, Daniel S.
    IEEE TRANSACTIONS ON MEDICAL ROBOTICS AND BIONICS, 2022, 4 (02): : 331 - 334
  • [38] Self-supervised coarse-to-fine monocular depth estimation using a lightweight attention module
    Li, Yuanzhen
    Luo, Fei
    Xiao, Chunxia
    COMPUTATIONAL VISUAL MEDIA, 2022, 8 (04) : 631 - 647
  • [39] Monocular Depth Estimation via Self-Supervised Self-Distillation
    Hu, Haifeng
    Feng, Yuyang
    Li, Dapeng
    Zhang, Suofei
    Zhao, Haitao
    SENSORS, 2024, 24 (13)
  • [40] Self-Supervised Monocular Depth Estimation by Digging into Uncertainty Quantification
    Li, Yuan-Zhen
    Zheng, Sheng-Jie
    Tan, Zi-Xin
    Cao, Tuo
    Luo, Fei
    Xiao, Chun-Xia
    JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2023, 38 (03) : 510 - 525