Video-based point cloud compression artifact removal based on the geometry video enhancement

被引:1
|
作者
Wu, Fan [1 ]
Shen, Liquan [1 ]
Chen, Tianyi [1 ]
Wang, Feifeng [1 ]
机构
[1] Shanghai Univ, Sch Commun & Informat Engn, Shanghai, Peoples R China
关键词
compressed distortion restoration; point cloud enhancement; quantization; video-based point cloud compression; gradient guidance;
D O I
10.1117/1.JEI.33.2.023004
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Video-based point cloud compression projects dynamic point clouds to 2D videos called geometry videos and texture videos for compression and transmission. In the geometry video, the pixel values represent the positions of each point in the point cloud. Due to distortion of the geometry video, there are some holes and noise points in the reconstructed point cloud. The previous methods for enhancing 2D images or videos can be applied to improve the quality of geometry videos. However, there will still be limitations in the reconstructed 3D point cloud because these methods do not take into account the feature of the 3D point cloud, such as the shape changes and surface orientations. To overcome these limitations, we propose an enhancement network specifically designed for point cloud enhancement through restoring geometry videos, which can calibrate the shape variations and surface orientations of point clouds. Specifically, the gradient information of the geometry video reflects the changes in pixel values, which correspond to changes in shape of the point cloud. Additionally, the normal vectors of the points in the point cloud provide the point cloud surface orientation information. To attain similarity of the shape changes, we design a two-branch network structure and utilize an additional branch comprising of gradient information restoring module to restore the gradient information of the geometry video. To ensure the consistency of point normal vectors, surface fitting and estimation module is designed to calculate the normal vectors of the points in distorted point cloud and the original point cloud through the geometry video, and then the difference of these normal vectors can be used to guide the restoration of the geometry video. Our method has been proved to be satisfactory through the validation experiments on currently available point cloud sequences. (c) 2024 SPIE and IS&T
引用
收藏
页数:22
相关论文
共 50 条
  • [21] OCCUPANCY-MAP-BASED RATE DISTORTION OPTIMIZATION FOR VIDEO-BASED POINT CLOUD COMPRESSION
    Li, Li
    Li, Zhu
    Liu, Shan
    Li, Houqiang
    2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 3167 - 3171
  • [22] Fast Grid-Based Refining Segmentation Method in Video-Based Point Cloud Compression
    Kim, Jieon
    Kim, Yong-Hwan
    IEEE ACCESS, 2021, 9 : 80088 - 80099
  • [23] Chain Code-Based Occupancy Map Coding for Video-Based Point Cloud Compression
    Yang, Runyu
    Yan, Ning
    Li, Li
    Liu, Dong
    Wu, Feng
    2020 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP), 2020, : 479 - 482
  • [24] VPU: A Video-Based Point Cloud Upsampling Framework
    Wang, Kaisiyuan
    Sheng, Lu
    Gu, Shuhang
    Xu, Dong
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 4062 - 4075
  • [25] Enhanced Temporal Consistency for Global Patch Allocation in Video-Based Point Cloud Compression
    Chiang, Jui-Chiu
    Wu, Yu-Tze
    Hsieh, Hsin-Yun
    Tsai, Yun-Chang
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 6917 - 6930
  • [26] Model-Based Joint Bit Allocation Between Geometry and Color for Video-Based 3D Point Cloud Compression
    Liu, Qi
    Yuan, Hui
    Hou, Junhui
    Hamzaoui, Raouf
    Su, Honglei
    IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23 : 3278 - 3291
  • [27] Simple Grid-Based Refinement Segmentation Algorithm for MPEG Video-Based Point Cloud Compression
    Jia, Qiong
    Kim, Kyutae
    Lee, Min Ku
    Jang, Euee S.
    IEEE ACCESS, 2024, 12 : 23695 - 23706
  • [28] Occupancy-Map-Based Rate Distortion Optimization and Partition for Video-Based Point Cloud Compression
    Li, Li
    Li, Zhu
    Liu, Shan
    Li, Houqiang
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2021, 31 (01) : 326 - 338
  • [29] Occupancy map-based low complexity motion prediction for video-based point cloud compression
    Wang, Yihan
    Wang, Yongfang
    Cui, Tengyao
    Fang, Zhijun
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2024, 100
  • [30] Differential Transform for Video-Based Plenoptic Point Cloud Coding
    Garcia, Diogo C.
    Dorea, Camilo
    Ferreira, Renan U. B.
    Freitas, Davi R.
    de Queiroz, Ricardo L.
    Higa, Rogerio
    Seidel, Ismael
    Testoni, Vanessa
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 1994 - 2003