Deep Geometry Post-Processing for Decompressed Point Clouds
- URL: http://arxiv.org/abs/2204.13952v1
- Date: Fri, 29 Apr 2022 08:57:03 GMT
- Title: Deep Geometry Post-Processing for Decompressed Point Clouds
- Authors: Xiaoqing Fan, Ge Li, Dingquan Li, Yurui Ren, Wei Gao, Thomas H. Li
- Abstract summary: Point cloud compression plays a crucial role in reducing the huge cost of data storage and transmission.
We propose a novel learning-based post-processing method to enhance the decompressed point clouds.
Experimental results show that the proposed method can significantly improve the quality of the decompressed point clouds.
- Score: 32.72083309729585
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- PIVOT-Net: Heterogeneous Point-Voxel-Tree-based Framework for Point
Cloud Compression [8.778300313732027]
We propose a heterogeneous point cloud compression (PCC) framework.
We unify typical point cloud representations -- point-based, voxel-based, and tree-based representations -- and their associated backbones.
We augment the framework with a proposed context-aware upsampling for decoding and an enhanced voxel transformer for feature aggregation.
arXiv Detail & Related papers (2024-02-11T16:57:08Z) - Arbitrary point cloud upsampling via Dual Back-Projection Network [12.344557879284219]
We propose a Dual Back-Projection network for point cloud upsampling (DBPnet)
A Dual Back-Projection is formulated in an up-down-up manner for point cloud upsampling.
Experimental results show that the proposed method achieves the lowest point set matching losses.
arXiv Detail & Related papers (2023-07-18T06:11:09Z) - Geometric Prior Based Deep Human Point Cloud Geometry Compression [67.49785946369055]
We leverage the human geometric prior in geometry redundancy removal of point clouds.
We can envisage high-resolution human point clouds as a combination of geometric priors and structural deviations.
The proposed framework can operate in a play-and-plug fashion with existing learning based point cloud compression methods.
arXiv Detail & Related papers (2023-05-02T10:35:20Z) - Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent
with Learned Distance Functions [77.32043242988738]
We propose a new framework for accurate point cloud upsampling that supports arbitrary upsampling rates.
Our method first interpolates the low-res point cloud according to a given upsampling rate.
arXiv Detail & Related papers (2023-04-24T06:36:35Z) - GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud
Compression [16.98171403698783]
We propose a heterogeneous approach with deep learning for lossy point cloud geometry compression.
Specifically, a point-based network is applied to convert the erratic local details to latent features residing on the coarse point cloud.
arXiv Detail & Related papers (2022-09-09T17:09:02Z) - Density-preserving Deep Point Cloud Compression [72.0703956923403]
We propose a novel deep point cloud compression method that preserves local density information.
Our method works in an auto-encoder fashion: the encoder downsamples the points and learns point-wise features, while the decoder upsamples the points using these features.
arXiv Detail & Related papers (2022-04-27T03:42:15Z) - Variable Rate Compression for Raw 3D Point Clouds [5.107705550575662]
We propose a novel variable rate deep compression architecture that operates on raw 3D point cloud data.
Our network is capable of explicitly processing point clouds and generating a compressed description.
arXiv Detail & Related papers (2022-02-28T15:15:39Z) - A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud
Completion [69.32451612060214]
Real-scanned 3D point clouds are often incomplete, and it is important to recover complete point clouds for downstream applications.
Most existing point cloud completion methods use Chamfer Distance (CD) loss for training.
We propose a novel Point Diffusion-Refinement (PDR) paradigm for point cloud completion.
arXiv Detail & Related papers (2021-12-07T06:59:06Z) - Learning Gradient Fields for Shape Generation [69.85355757242075]
A point cloud can be viewed as samples from a distribution of 3D points whose density is concentrated near the surface of the shape.
We generate point clouds by performing gradient ascent on an unnormalized probability density.
Our model directly predicts the gradient of the log density field and can be trained with a simple objective adapted from score-based generative models.
arXiv Detail & Related papers (2020-08-14T18:06:15Z) - GRNet: Gridding Residual Network for Dense Point Cloud Completion [54.43648460932248]
Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications.
We propose a novel Gridding Residual Network (GRNet) for point cloud completion.
Experimental results indicate that the proposed GRNet performs favorably against state-of-the-art methods on the ShapeNet, Completion3D, and KITTI benchmarks.
arXiv Detail & Related papers (2020-06-06T02:46:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.