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
  • [1] SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
    Wei, Yi
    Zhao, Linqing
    Zheng, Wenzhao
    Zhu, Zheng
    Rao, Yongming
    Huang, Guan
    Lu, Jiwen
    Zhou, Jie
    CONFERENCE ON ROBOT LEARNING, VOL 205, 2022, 205 : 539 - 549
  • [2] M2Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation
    Zou, Yingshuang
    Ding, Yikang
    Qiu, Xi
    Wang, Haoqian
    Zhang, Haotian
    COMPUTER VISION-ECCV 2024, PT XLVI, 2025, 15104 : 269 - 285
  • [3] Self-supervised recurrent depth estimation with attention mechanisms
    Makarov I.
    Bakhanova M.
    Nikolenko S.
    Gerasimova O.
    PeerJ Computer Science, 2022, 8
  • [4] Self-supervised recurrent depth estimation with attention mechanisms
    Makarov, Ilya
    Bakhanova, Maria
    Nikolenko, Sergey
    Gerasimova, Olga
    PEERJ COMPUTER SCIENCE, 2022, 8
  • [5] Self-supervised recurrent depth estimation with attention mechanisms
    Makarov, Ilya
    Bakhanova, Maria
    Nikolenko, Sergey
    Gerasimova, Olga
    PEERJ, 2022, 8
  • [6] Towards Keypoint Guided Self-supervised Depth Estimation
    Bartol, Kristijan
    Bojanic, David
    Petkovic, Tomislav
    Pribanic, Tomislav
    Donoso, Yago
    VISAPP: PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 4: VISAPP, 2020, : 583 - 589
  • [7] Semantically guided self-supervised monocular depth estimation
    Lu, Xiao
    Sun, Haoran
    Wang, Xiuling
    Zhang, Zhiguo
    Wang, Haixia
    IET IMAGE PROCESSING, 2022, 16 (05) : 1293 - 1304
  • [8] Embodiment: Self-Supervised Depth Estimation Based on Camera Models
    Zhang, Jinchang
    Reddy, Praveen Kumar
    Wong, Xue-Iuan
    Aloimonos, Yiannis
    Lu, Guoyu
    2024 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2024), 2024, : 7809 - 7816
  • [9] MonoVAN: Visual Attention for Self-Supervised Monocular Depth Estimation
    Indyk, Ilia
    Makarov, Ilya
    2023 IEEE INTERNATIONAL SYMPOSIUM ON MIXED AND AUGMENTED REALITY, ISMAR, 2023, : 1211 - 1220
  • [10] Self-Supervised Monocular Depth Estimation Based on Channel Attention
    Tao, Bo
    Chen, Xinbo
    Tong, Xiliang
    Jiang, Du
    Chen, Baojia
    PHOTONICS, 2022, 9 (06)