EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimation

被引:5
|
作者
Shi, Yunxiao [1 ]
Cai, Hong [1 ]
Ansari, Amin [2 ]
Porikli, Fatih [1 ]
机构
[1] Qualcomm AI Res, San Diego, CA 92121 USA
[2] Qualcomm Technol Inc, San Diego, CA USA
关键词
D O I
10.1109/CVPRW59228.2023.00017
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The ubiquitous multi-camera setup on modern autonomous vehicles provides an opportunity to construct surround-view depth. Existing methods, however, either perform independent monocular depth estimations on each camera or rely on computationally heavy self attention mechanisms. In this paper, we propose a novel guided attention architecture, EGA-Depth, which can improve both the efficiency and accuracy of self-supervised multi-camera depth estimation. More specifically, for each camera, we use its perspective view as the query to cross-reference its neighboring views to derive informative features for this camera view. This allows the model to perform attention only across views with considerable overlaps and avoid the costly computations of standard self-attention. Given its efficiency, EGA-Depth enables us to exploit higher-resolution visual features, leading to improved accuracy. Furthermore, EGA-Depth can incorporate more frames from previous time steps as it scales linearly w.r.t. the number of views and frames. Extensive experiments on two challenging autonomous driving benchmarks nuScenes and DDAD demonstrate the efficacy of our proposed EGA-Depth and show that it achieves the new state-of-the-art in self-supervised multi-camera depth estimation.
引用
收藏
页码:119 / 129
页数:11
相关论文
共 50 条
  • [31] PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation
    Dong, Yue-Jiang
    Guo, Yuan-Chen
    Liu, Ying-Tian
    Zhang, Fang-Lue
    Zhang, Song-Hai
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 2, 2024, : 1609 - 1617
  • [32] LAM-Depth: Laplace-Attention Module-Based Self-Supervised Monocular Depth Estimation
    Wei, Jiansheng
    Pan, Shuguo
    Gao, Wang
    Guo, Peng
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, 25 (10) : 13706 - 13716
  • [33] Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
    Wang, Kun
    Zhang, Zhenyu
    Yan, Zhiqiang
    Li, Xiang
    Xu, Baobei
    Li, Jun
    Yang, Jian
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 16035 - 16044
  • [34] Joint Self-Supervised Monocular Depth Estimation and SLAM
    Xing, Xiaoxia
    Cai, Yinghao
    Lu, Tao
    Yang, Yiping
    Wen, Dayong
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 4030 - 4036
  • [35] HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation
    Lyu, Xiaoyang
    Liu, Liang
    Wang, Mengmeng
    Kong, Xin
    Liu, Lina
    Liu, Yong
    Chen, Xinxin
    Yuan, Yi
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 2294 - 2301
  • [36] Self-Supervised Monocular Scene Decomposition and Depth Estimation
    Safadoust, Sadra
    Guney, Fatma
    2021 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2021), 2021, : 627 - 636
  • [37] Learn to Adapt for Self-Supervised Monocular Depth Estimation
    Sun, Qiyu
    Yen, Gary G.
    Tang, Yang
    Zhao, Chaoqiang
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (11) : 15647 - 15659
  • [38] Self-Supervised Monocular Depth Estimation With Multiscale Perception
    Zhang, Yourun
    Gong, Maoguo
    Li, Jianzhao
    Zhang, Mingyang
    Jiang, Fenlong
    Zhao, Hongyu
    IEEE Transactions on Image Processing, 2022, 31 : 3251 - 3266
  • [39] Self-Supervised Monocular Depth Estimation With Multiscale Perception
    Zhang, Yourun
    Gong, Maoguo
    Li, Jianzhao
    Zhang, Mingyang
    Jiang, Fenlong
    Zhao, Hongyu
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 3251 - 3266
  • [40] RA-Depth: Resolution Adaptive Self-supervised Monocular Depth Estimation
    He, Mu
    Hui, Le
    Bian, Yikai
    Ren, Jian
    Xie, Jin
    Yang, Jian
    COMPUTER VISION - ECCV 2022, PT XXVII, 2022, 13687 : 565 - 581