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
  • [41] Adv-Depth: Self-Supervised Monocular Depth Estimation With an Adversarial Loss
    Li, Kunhong
    Fu, Zhiheng
    Wang, Hanyun
    Chen, Zonghao
    Guo, Yulan
    IEEE SIGNAL PROCESSING LETTERS, 2021, 28 : 638 - 642
  • [42] Self-Supervised Monocular Depth Estimation With Extensive Pretraining
    Choi, Hyukdoo
    IEEE ACCESS, 2021, 9 : 157236 - 157246
  • [43] Self-Supervised Monocular Depth Estimation with Extensive Pretraining
    Choi, Hyukdoo
    IEEE Access, 2021, 9 : 157236 - 157246
  • [44] Self-supervised monocular depth estimation for gastrointestinal endoscopy
    Liu, Yuying
    Zuo, Siyang
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2023, 238
  • [45] Adaptive Self-supervised Depth Estimation in Monocular Videos
    Mendoza, Julio
    Pedrini, Helio
    IMAGE AND GRAPHICS (ICIG 2021), PT III, 2021, 12890 : 687 - 699
  • [46] Self-supervised monocular depth estimation with direct methods
    Wang, Haixia
    Sun, Yehao
    Wu, Q. M. Jonathan
    Lu, Xiao
    Wang, Xiuling
    Zhang, Zhiguo
    NEUROCOMPUTING, 2021, 421 : 340 - 348
  • [47] Self-supervised monocular depth estimation with direct methods
    Wang H.
    Sun Y.
    Wu Q.M.J.
    Lu X.
    Wang X.
    Zhang Z.
    Neurocomputing, 2021, 421 : 340 - 348
  • [48] 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
  • [49] Self-supervised monocular depth estimation via joint attention and intelligent mask loss
    Guo, Peng
    Pan, Shuguo
    Gao, Wang
    Khoshelham, Kourosh
    MACHINE VISION AND APPLICATIONS, 2025, 36 (01)
  • [50] Self-supervised Monocular Trained Depth Estimation Using Triplet Attention and Funnel Activation
    Xiang, Xuezhi
    Kong, Xiangdong
    Qiu, Yujian
    Zhang, Kaixu
    Lv, Ning
    NEURAL PROCESSING LETTERS, 2021, 53 (06) : 4489 - 4506