A Survey of CNN-Based Techniques for Scene Flow Estimation

被引:0
|
作者
Muthu, Sundaram [1 ,2 ]
Tennakoon, Ruwan [3 ]
Hoseinnezhad, Reza [2 ]
Bab-Hadiashar, Alireza [2 ]
机构
[1] CSIRO, Data61, Imaging & Comp Vis, Canberra, ACT 2601, Australia
[2] RMIT Univ, Sch Engn, Melbourne, Vic 3000, Australia
[3] RMIT Univ, Sch Comp Technol, Melbourne, Vic 3000, Australia
基金
澳大利亚研究理事会;
关键词
Scene flow estimation; learning-based methods; self-supervised; STEREO; MOTION; SPARSE;
D O I
10.1109/ACCESS.2023.3314188
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The analysis of 3D motion information is the key to solve various computer vision tasks. Scene flow estimation tackles the problem of obtaining the 3D motion field. In this paper, we review the recent scene flow estimation papers with a focus on learning-based methods. The problem formulation, challenges and applications are introduced. The existing datasets and performance metrics are presented. The reason behind learning-based methods replacing the traditional variational methods are discussed. CNN-based scene flow estimation methods are then categorized with respect to the level of supervision, data-availability and the number of steps involved in obtaining the results. The performance of different methods on the well known KITTI and FlyingThings3D datasets are tabulated. Their relative advantages and limitations are then analysed. Future trends and some open problems in the estimation of scene flow are discussed with special focus on the self-supervised methods that does not require labelled training data.
引用
收藏
页码:99289 / 99303
页数:15
相关论文
共 50 条
  • [1] A survey of variational and CNN-based optical flow techniques
    Tu, Zhigang
    Xie, Wei
    Zhang, Dejun
    Poppe, Ronald
    Veltkamp, Remco C.
    Li, Baoxin
    Yuan, Junsong
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2019, 72 : 9 - 24
  • [2] CNN-Based Acoustic Scene Classification System
    Lee, Yerin
    Lim, Soyoung
    Kwak, Il-Youp
    ELECTRONICS, 2021, 10 (04) : 1 - 16
  • [3] Simultaneous Attack on CNN-Based Monocular Depth Estimation and Optical Flow Estimation
    Yamanaka, Koichiro
    Takahashi, Keita
    Fujii, Toshiaki
    Matsumoto, Ryuraroh
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2021, E104D (05): : 785 - 788
  • [4] CNN-based Rescaling Factor Estimation
    Liu, Chang
    Kirchner, Matthias
    IH&MMSEC '19: PROCEEDINGS OF THE ACM WORKSHOP ON INFORMATION HIDING AND MULTIMEDIA SECURITY, 2019, : 119 - 124
  • [5] CNN-BASED INITIAL BACKGROUND ESTIMATION
    Halfaoui, Ibrahim
    Bouzaraa, Fahd
    Urfalioglu, Onay
    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 101 - 106
  • [6] A Survey of CNN-Based Network Intrusion Detection
    Mohammadpour, Leila
    Ling, Teck Chaw
    Liew, Chee Sun
    Aryanfar, Alihossein
    APPLIED SCIENCES-BASEL, 2022, 12 (16):
  • [7] CNN-Based Simultaneous Dehazing and Depth Estimation
    Lee, Byeong-Uk
    Lee, Kyunghyun
    Oh, Jean
    Kweon, In So
    2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2020, : 9722 - 9728
  • [8] CNN-Based Illumination Estimation with Semantic Information
    Choi, Ho-Hyoung
    Kang, Hyun-Soo
    Yun, Byoung-Ju
    APPLIED SCIENCES-BASEL, 2020, 10 (14):
  • [9] ENHANCING SOUND TEXTURE IN CNN-BASED ACOUSTIC SCENE CLASSIFICATION
    Wu, Yuzhong
    Lee, Tan
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 815 - 819
  • [10] A survey of recent advances in CNN-based single image crowd counting and density estimation
    Sindagi, Vishwanath A.
    Patel, Vishal M.
    PATTERN RECOGNITION LETTERS, 2018, 107 : 3 - 16