• Chinese Journal of Lasers
  • Vol. 46, Issue 10, 1009002 (2019)
Decheng Wang1,*, Xiangning Chen1, Hui Yi1, and Feng Zhao1,2
Author Affiliations
  • 1School of Space Information, Space Engineering University of PLA, Beijing 101416, China
  • 261618 Troops of Chinese People's Liberation Army, Beijing 100094, China
  • show less
    DOI: 10.3788/CJL201946.1009002 Cite this Article Set citation alerts
    Decheng Wang, Xiangning Chen, Hui Yi, Feng Zhao. Hole Filling and Optimization Algorithm for Depth Images Based on Adaptive Joint Bilateral Filtering[J]. Chinese Journal of Lasers, 2019, 46(10): 1009002 Copy Citation Text show less
    Diagram of improved adaptive depth image inpainting algorithm
    Fig. 1. Diagram of improved adaptive depth image inpainting algorithm
    Image registration results acquired from Kinect v2 sensor. (a) Color image; (b) depth image
    Fig. 2. Image registration results acquired from Kinect v2 sensor. (a) Color image; (b) depth image
    Hole addition and inpainting results of partial depth images in Middlebury dataset. (a) Original color images; (b) original depth images; (c) depth images and details after adding holes to simulate noise; (d) depth images and details improved by proposed method
    Fig. 3. Hole addition and inpainting results of partial depth images in Middlebury dataset. (a) Original color images; (b) original depth images; (c) depth images and details after adding holes to simulate noise; (d) depth images and details improved by proposed method
    Comparison of results obtained by proposed method and other methods. (a) Original color images; (b) original depth images; (c) results of joint bilateral filter; (d) results of Ref. [20]; (e) results of propsoed algorithm
    Fig. 4. Comparison of results obtained by proposed method and other methods. (a) Original color images; (b) original depth images; (c) results of joint bilateral filter; (d) results of Ref. [20]; (e) results of propsoed algorithm
    RMSE comparison of proposed algorithm and other methods based on the Middlebury dataset
    Fig. 5. RMSE comparison of proposed algorithm and other methods based on the Middlebury dataset
    IndexArtMoebiusReindeerDolls
    RMSE4.53872.52184.41432.1907
    PSNR /dB34.992340.096635.233541.3192
    SSIM0.89510.93650.90270.9418
    Time /s0.13621.11452.86810.2413
    Table 1. Quantitative indicators based on partial image restoration on Middlebury dataset
    Decheng Wang, Xiangning Chen, Hui Yi, Feng Zhao. Hole Filling and Optimization Algorithm for Depth Images Based on Adaptive Joint Bilateral Filtering[J]. Chinese Journal of Lasers, 2019, 46(10): 1009002
    Download Citation