Acta Optica Sinica, Volume. 43, Issue 14, 1415001(2023)

Monocular Depth Estimation Method Based on Plane Coefficient Representation with Adaptive Depth Distribution

Jiajun Wang, Yue Liu*, Yuhui Wu, Hao Sha, and Yongtian Wang
Author Affiliations
  • Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China
  • show less
    Figures & Tables(12)
    Schematic diagram of pixel depth distribution of different images in indoor scene. (a) Image with maximum depth unconstrained; (b) image with maximum depth constrained; (c) close-up image of furniture
    Structure diagram of image depth distribution prediction module
    Overall architecture of monocular depth estimation network. (a),(b) Subnetwork structure
    Visual comparison of proposed method with other methods on NYU Depth-v2 dataset
    Visual comparison of three-dimensional reconstruction of proposed method with other methods
    Qualitative and quantitative comparison of depth distribution of proposed method with other methods
    Failure predictions of proposed method on NYU Depth-v2 dataset
    • Table 1. Quantitative comparison of proposed method with other methods on NYU Depth-v2 dataset

      View table

      Table 1. Quantitative comparison of proposed method with other methods on NYU Depth-v2 dataset

      MethodRMSERELlgδ<1.25δ<1.252δ<1.253Params /M
      Eigen et al.130.6410.1580.7690.9500.988141
      Laina et al.420.5730.1270.0550.8110.9530.98864
      Hao et al.430.5550.1270.0530.8410.9660.99160
      Fu et al.440.5090.1150.0510.8280.9650.992110
      Hu et al.450.5300.1150.0500.8660.9750.993157
      Raman et al.460.4950.1390.0470.8880.9790.99580.4
      Lee et al.180.4190.1190.0510.8650.9750.99349.5
      Yin et al.280.4160.1080.0480.8780.9770.994114.2
      Proposed0.4160.1210.0500.8640.9740.99546
    • Table 2. Inference speed comparison of proposed method with other methods

      View table

      Table 2. Inference speed comparison of proposed method with other methods

      MethodRunning time /msFrame rate /(frame·s-1RMSEParams /M

      Laina et al.42

      Fu et al.44

      Hu et al.45

      36

      35

      91

      27

      28

      11

      0.573

      0.509

      0.530

      64

      110

      157

      Raman et al.4621410.49580.4

      Lee et al.18

      Yin et al.28

      60

      36

      16

      27

      0.419

      0.416

      49.5

      114.2

      Proposed30330.41646
    • Table 3. Comparison of IoU results of proposed method with other methods on test set

      View table

      Table 3. Comparison of IoU results of proposed method with other methods on test set

      MethodDIoU
      Fu et al.440.863
      Yin et al.280.805
      Raman et al.460.883
      Hu et al.450.887
      Proposed0.914
    • Table 4. Quantitative results of ablation experiments based on network architecture

      View table

      Table 4. Quantitative results of ablation experiments based on network architecture

      MethodRMSERELlgδ<1.25δ<1.252δ<1.253
      Depth distribution predictor0.4300.1270.0520.8530.9710.994
      Plane coefficient representations0.4200.1230.0510.8620.9750.995
      Baseline0.4160.1210.0500.8640.9740.995
    • Table 5. Quantitative results of ablation experiments based on network loss function

      View table

      Table 5. Quantitative results of ablation experiments based on network loss function

      MethodRMSERELlgδ<1.25δ<1.252δ<1.253
      Baseline0.4310.1250.0520.8570.9710.994
      With Ledge0.4280.1240.0510.8580.9730.994
      With Ledge and Lvir0.4260.1230.0510.8590.9730.994
      With Ledge and Ldis0.4180.1220.0500.8620.9740.995
      With LedgeLdis,and Lvir0.4160.1210.0500.8640.9740.995
    Tools

    Get Citation

    Copy Citation Text

    Jiajun Wang, Yue Liu, Yuhui Wu, Hao Sha, Yongtian Wang. Monocular Depth Estimation Method Based on Plane Coefficient Representation with Adaptive Depth Distribution[J]. Acta Optica Sinica, 2023, 43(14): 1415001

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Machine Vision

    Received: Jan. 12, 2023

    Accepted: Mar. 20, 2023

    Published Online: Jul. 13, 2023

    The Author Email: Yue Liu (liuyue@bit.edu.cn)

    DOI:10.3788/AOS230468

    Topics