Depth Completion using Geometry-Aware Embedding

被引:21
|
作者
Du, Wenchao [1 ]
Chen, Hu [1 ]
Yang, Hongyu [1 ]
Zhang, Yi [1 ]
机构
[1] Sichuan Univ, Coll Comp Sci, Chengdu 610065, Peoples R China
关键词
NETWORK; SPARSE;
D O I
10.1109/ICRA46639.2022.9811556
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Exploiting internal spatial geometric constraints of sparse LiDARs is beneficial to depth completion, however, has been not explored well. This paper proposes an efficient method to learn geometry-aware embedding, which encodes the local and global geometric structure information from 3D points, e.g., scene layout, object's sizes and shapes, to guide dense depth estimation. Specifically, we utilize the dynamic graph representation to model generalized geometric relationship from irregular point clouds in a flexible and efficient manner. Further, we joint this embedding and corresponded RGB appearance information to infer missing depths of the scene with well structure-preserved details. The key to our method is to integrate implicit 3D geometric representation into a 2D learning architecture, which leads to a better trade-off between the performance and efficiency. Extensive experiments demonstrate that the proposed method outperforms previous works and could reconstruct fine depths with crisp boundaries in regions that are over-smoothed by them. The ablation study gives more insights into our method that could achieve significant gains with a simple design, while having better generalization capability and stability. The code is available at https://github.com/Wenchao-Du/GAENet.
引用
收藏
页码:8680 / 8686
页数:7
相关论文
共 50 条
  • [31] Learning to Match Features with Geometry-Aware Pooling
    Deng, Jiaxin
    Yang, Xu
    Zheng, Suiwu
    NEURAL INFORMATION PROCESSING, ICONIP 2023, PT VI, 2024, 14452 : 292 - 302
  • [32] Discriminative and Geometry-Aware Unsupervised Domain Adaptation
    Luo, Lingkun
    Chen, Liming
    Hu, Shiqiang
    Lu, Ying
    Wang, Xiaofang
    IEEE TRANSACTIONS ON CYBERNETICS, 2020, 50 (09) : 3914 - 3927
  • [33] GEOMETRY-AWARE GAN FOR FACE ATTRIBUTE TRANSFER
    Huang, Danlan
    Tao, Xiaoming
    Lu, Jianhua
    Do, Minh N.
    2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 729 - 733
  • [34] Geometry-Aware Volume-of-Fluid Method
    Cho, Junghyun
    Ko, Hyeong-Seok
    COMPUTER GRAPHICS FORUM, 2013, 32 (02) : 379 - 388
  • [35] Geometry-Aware Generation of Adversarial Point Clouds
    Wen, Yuxin
    Lin, Jiehong
    Chen, Ke
    Chen, C. L. Philip
    Jia, Kui
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (06) : 2984 - 2999
  • [36] Geometry-Aware Weight Perturbation for Adversarial Training
    Jiang, Yixuan
    Chiang, Hsiao-Dong
    ELECTRONICS, 2024, 13 (17)
  • [37] GAGAN: Geometry-Aware Generative Adversarial Networks
    Kossaifi, Jean
    Linh Tran
    Panagakis, Yannis
    Pantic, Maja
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 878 - 887
  • [38] Unsupervised Geometry-Aware Deep LiDAR Odometry
    Cho, Younggun
    Kim, Giseop
    Kim, Ayoung
    2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2020, : 2145 - 2152
  • [39] Geometry-Aware GAN for Face Attribute Transfer
    Huang, Danlan
    Tao, Xiaoming
    Lu, Jianhua
    Do, Minh N.
    IEEE ACCESS, 2019, 7 : 145953 - 145969
  • [40] Geometry-Aware Distillation for Indoor Semantic Segmentation
    Jiao, Jianbo
    Wei, Yunchao
    Jie, Zequn
    Shi, Honghui
    Lau, Rynson
    Huang, Thomas S.
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 2864 - 2873