Convolutional Neural Network-Based Occupancy Map Accuracy Improvement for Video-Based Point Cloud Compression

Jia, Wei; Li, Li; Akhtar, Anique; Zhu, Li; Liu, Shan

doi:10.1109/tmm.2021.3079698

Cited by 24 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The post-processing task aims to improve the quality of the decompressed point clouds. Some methods based on V-PCC attempt to refine the occupancy map [17] or the near and far depth maps [18] to improve the quality of the decompressed point clouds. Besides, some other methods have been proposed to alleviate the problem of missing points caused by quantization in G-PCC.…”

Section: Post-processing Methodsmentioning

confidence: 99%

Deep Geometry Post-Processing for Decompressed Point Clouds

Fan¹,

Li²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Point cloud compression plays a crucial role in reducing the huge cost of data storage and transmission. However, distortions can be introduced into the decompressed point clouds due to quantization. In this paper, we propose a novel learning-based post-processing method to enhance the decompressed point clouds. Specifically, a voxelized point cloud is first divided into small cubes. Then, a 3D convolutional network is proposed to predict the occupancy probability for each location of a cube. We leverage both local and global contexts by generating multi-scale probabilities. These probabilities are progressively summed to predict the results in a coarse-to-fine manner. Finally, we obtain the geometry-refined point clouds based on the predicted probabilities. Different from previous methods, we deal with decompressed point clouds with huge variety of distortions using a single model. Experimental results show that the proposed method can significantly improve the quality of the decompressed point clouds, achieving 9.30dB BDPSNR gain on three representative datasets on average.

show abstract

Section: Post-processing Methodsmentioning

confidence: 99%

Deep Geometry Post-Processing for Decompressed Point Clouds

Fan¹,

Li²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, some methods have been continuously proposed to solve the V-PCC problem. 29,33,34 Method Ref. 33 consists of point cloud sampling, ghost artifact removal network, and aggregation scheme.…”

Section: Point Cloud Enhancement and Denoisingmentioning

confidence: 99%

“…It uses 3D deep convolutional feature learning to remove geometric artifacts and employs projection prior and quantization prior to recover quantization directions and noise levels. Jia et al 34 introduced OGCNN to improve the accuracy of occupancy grid map, thereby enhancing the quality of reconstructed 3D point clouds. Chen et al 29 proposed a deep-learning-based attribute map enhancement method based on the guidance of occupancy map.…”

Section: Point Cloud Enhancement and Denoisingmentioning

confidence: 99%

See 1 more Smart Citation

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

Wu,

Shen,

Chen

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

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.

show abstract

“…In addition, due to storing and analyzing an illimitable amount of data is just possible in cloud computing, in [325], a method for predicting the amount of data requisite cloud services has been presented that is a hierarchical Pythagorean fuzzy deep neural network. Furthermore, in order to improve the accuracy of occupancy map videos, the authors in [326] implement a Convolutional Neural Network (CNN). They claimed that this is the first learning-based work to improve the performance of Videobased point Cloud Compression (V-PCC).…”

Section: Ai In Cloudmentioning

confidence: 99%

Privacy-Preserving Cloud Computing: Ecosystem, Life Cycle, Layered Architecture and Future Roadmap

Ahmadi¹,

Salehfar²

2022

Preprint

View full text Add to dashboard Cite

Privacy-Preserving Cloud Computing is an emerging technology with many applications in various fields. Cloud computing is important because it allows for scalability, adaptability, and improved security. Likewise, privacy in cloud computing is important because it ensures that the integrity of data stored on the cloud maintains intact. This survey paper on privacy-preserving cloud computing can help pave the way for future research in related areas. This paper helps to identify existing trends by establishing a layered architecture along with a life cycle and an ecosystem for privacy-preserving cloud systems in addition to identifying the existing trends in research on this area.

show abstract

Convolutional Neural Network-Based Occupancy Map Accuracy Improvement for Video-Based Point Cloud Compression

Cited by 24 publications

References 23 publications

Deep Geometry Post-Processing for Decompressed Point Clouds

Deep Geometry Post-Processing for Decompressed Point Clouds

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

Privacy-Preserving Cloud Computing: Ecosystem, Life Cycle, Layered Architecture and Future Roadmap

Contact Info

Product

Resources

About