DEPTH ENHANCEMENT USING RGB-D GUIDED FILTERING

被引:0
|
作者
Hui, Tak-Wai [1 ]
Ngan, King Ngi [1 ]
机构
[1] Chinese Univ Hong Kong, Dept Elect Engn, Hong Kong, Hong Kong, Peoples R China
关键词
Depth enhancement; guided image filtering; hole filling; linear regression;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Depth maps from low-cost RGB-D system are generally noisy and not accurate enough. Holes often exist in the depth maps. Bilateral filter is commonly utilized to perform depth enhancement. However, it requires high computational time. Its texture transferring property also makes those boundaries between textured and homogeneous regions in the filtered depth map far from satisfactory. In this paper, we present a method to filter raw depth maps using a RGB-D guided filtering in a two-stage framework. Our method not only has a faster computational time than bilateral filter but also avoids the problem of over-texture transfer. We also use RGB-D frames to fill holes in the depth maps. This can effectively prevents depth bleeding artifacts.
引用
收藏
页码:3832 / 3836
页数:5
相关论文
共 50 条
  • [1] Fast Color-guided Depth Denoising for RGB-D Images by Graph Filtering
    Huang, Qiwei
    Li, Ruikang
    Jiang, Zidong
    Feng, Wei
    Lin, Sijie
    Feng, Hui
    Hu, Bo
    [J]. CONFERENCE RECORD OF THE 2019 FIFTY-THIRD ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, 2019, : 1811 - 1815
  • [2] PGDENet: Progressive Guided Fusion and Depth Enhancement Network for RGB-D Indoor Scene Parsing
    Zhou, Wujie
    Yang, Enquan
    Lei, Jingsheng
    Wan, Jian
    Yu, Lu
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 3483 - 3494
  • [3] Motion-Depth: RGB-D Depth Map Enhancement with Motion and Depth in Complement
    Hui, Tak-Wai
    Ngan, King Ngi
    [J]. 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, : 3962 - 3969
  • [4] Depth-Guided Disocclusion Inpainting of Synthesized RGB-D Images
    Buyssens, Pierre
    Le Meur, Olivier
    Daisy, Maxime
    Tschumperle, David
    Lezoray, Olivier
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (02) : 525 - 538
  • [5] Real-time depth enhancement by fusion for RGB-D cameras
    Garcia, Frederic
    Aouada, Djamila
    Solignac, Thomas
    Mirbach, Bruno
    Ottersten, Bjoern
    [J]. IET COMPUTER VISION, 2013, 7 (05) : 335 - 345
  • [6] Dense RGB-D visual odometry using inverse depth
    Gutierrez-Gomez, Daniel
    Mayol-Cuevas, Walterio
    Guerrero, J. J.
    [J]. ROBOTICS AND AUTONOMOUS SYSTEMS, 2016, 75 : 571 - 583
  • [7] Depth cue enhancement and guidance network for RGB-D salient object detection
    Li, Xiang
    Zhang, Qing
    Yan, Weiqi
    Dai, Meng
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2023, 95
  • [8] Color-Guided Depth Recovery From RGB-D Data Using an Adaptive Autoregressive Model
    Yang, Jingyu
    Ye, Xinchen
    Li, Kun
    Hou, Chunping
    Wang, Yao
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2014, 23 (08) : 3443 - 3458
  • [9] Kinect Depth Maps Preprocessing Based on RGB-D Data Clustering and Bilateral Filtering
    Du, Haiyang
    Miao, Zhenjiang
    [J]. 2015 CHINESE AUTOMATION CONGRESS (CAC), 2015, : 732 - 736
  • [10] Enhancement of RGB-D Image Alignment Using Fiducial Markers
    Madeira, Tiago
    Oliveira, Miguel
    Dias, Paulo
    [J]. SENSORS, 2020, 20 (05)