paper-with-me

Papers

Tensor-Train Point Cloud Compression and Efficient Approximate Nearest-Neighbor Search

2024-10-06 · Georgii Novikov, Alexander Gneushev, Alexey Kadeishvili, Ivan Oseledets

Nearest-neighbor search in large vector databases is crucial for various machine learning applications. This paper introduces a novel method using tensor-train (TT) low-rank tensor decomposition to efficiently represent point clouds and enable fast approximate nearest-neighbor searches. We propose a probabilistic interpretation and utilize density estimation losses like Sliced Wasserstein to train TT decompositions, resulting in robust point cloud compression. We reveal an inherent hierarchical structure within TT point clouds, facilitating efficient approximate nearest-neighbor searches. In our paper, we provide detailed insights into the methodology and conduct comprehensive comparisons with existing methods. We demonstrate its effectiveness in various scenarios, including out-of-distribution (OOD) detection problems and approximate nearest-neighbor (ANN) search tasks.

📄 PDF Abstract BibTeX arXiv:2410.04462

Code (0)

등록된 구현이 없습니다.

Tasks

Density EstimationOut of Distribution (OOD) DetectionTensor Decomposition

Similar Papers 제목 키워드 기반

Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model

2023-03-11 · Dat Thanh Nguyen, Andre Kaup

In recent years, we have witnessed the presence of point cloud data in many aspects of our life, from immersive media, autonomous driving to healthcare, although at the cost of a tremendous amount of data. In this paper,…

AttributeAutonomous Driving

Rendering-Oriented 3D Point Cloud Attribute Compression using Sparse Tensor-based Transformer

2024-11-12 · Xiao Huo, Junhui Hou, Shuai Wan, Fuzheng Yang

The evolution of 3D visualization techniques has fundamentally transformed how we interact with digital content. At the forefront of this change is point cloud technology, offering an immersive experience that surpasses …

AttributeData Compression

PCAC-GAN: A Sparse-Tensor-Based Generative Adversarial Network for 3D Point Cloud Attribute Compression

2024-07-08 · Xiaolong Mao, Hui Yuan, Xin Lu, Raouf Hamzaoui 외

Learning-based methods have proven successful in compressing geometric information for point clouds. For attribute compression, however, they still lag behind non-learning-based methods such as the MPEG G-PCC standard. T…

AttributeComputational EfficiencyGenerative Adversarial Network

End-to-end learned Lossy Dynamic Point Cloud Attribute Compression

2024-08-20 · Dat Thanh Nguyen, Daniel Zieger, Marc Stamminger, Andre Kaup

Recent advancements in point cloud compression have primarily emphasized geometry compression while comparatively fewer efforts have been dedicated to attribute compression. This study introduces an end-to-end learned dy…

Attribute

Learning-based Lossless Point Cloud Geometry Coding using Sparse Tensors

2022-04-11 · Dat Thanh Nguyen, Andre Kaup

Most point cloud compression methods operate in the voxel or octree domain which is not the original representation of point clouds. Those representations either remove the geometric information or require high computati…