Deep Geometry Post-Processing for Decompressed Point Clouds
| Autor: | Xiaoqing Fan, Ge Li, Dingquan Li, Yurui Ren, Wei Gao, Thomas H. Li |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
Computer Vision and Pattern Recognition (cs.CV) Image and Video Processing (eess.IV) Computer Science - Computer Vision and Pattern Recognition FOS: Electrical engineering electronic engineering information engineering Data_CODINGANDINFORMATIONTHEORY Electrical Engineering and Systems Science - Image and Video Processing |
| DOI: | 10.48550/arxiv.2204.13952 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|