Deep AutoEncoder-based Lossy Geometry Compression for Point Clouds
arXiv:1905.03691
Abstract
Point cloud is a fundamental 3D representation which is widely used in real world applications such as autonomous driving. As a newly-developed media format which is characterized by complexity and irregularity, point cloud creates a need for compression algorithms which are more flexible than existing codecs. Recently, autoencoders(AEs) have shown their effectiveness in many visual analysis tasks as well as image compression, which inspires us to employ it in point cloud compression. In this paper, we propose a general autoencoder-based architecture for lossy geometry point cloud compression. To the best of our knowledge, it is the first autoencoder-based geometry compression codec that directly takes point clouds as input rather than voxel grids or collections of images. Compared with handcrafted codecs, this approach adapts much more quickly to previously unseen media contents and media formats, meanwhile achieving competitive performance. Our architecture consists of a pointnet-based encoder, a uniform quantizer, an entropy estimation block and a nonlinear synthesis transformation module. In lossy geometry compression of point cloud, results show that the proposed method outperforms the test model for categories 1 and 3 (TMC13) published by MPEG-3DG group on the 125th meeting, and on average a 73.15\% BD-rate gain is achieved.
References in corpus (5)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Variational image compression with a scale hyperprior
- End-to-end Optimized Image Compression
- Learning Representations and Generative Models for 3D Point Clouds
- SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
Cited by in corpus (8)
- Learned Point Cloud Geometry Compression
- GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compression
- Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model
- Patch-Based Deep Autoencoder for Point Cloud Geometry Compression
- Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions
- VoxelContext-Net: An Octree based Framework for Point Cloud Compression
- Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression
- Deep Implicit Volume Compression