Tensor-train Point Cloud Compression And Efficient Approximate Nearest-neighbor Search

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynovikov2024tensor

Related papers

• Connecting Compression Spaces With Transformer For Approximate Nearest Neighbor Search (2021)4.52
• Lossless Compression Of Vector Ids For Approximate Nearest Neighbor Search (2025)11.11
• PM-LSH: A Fast And Accurate In-memory Framework For High-dimensional Approximate NN And Closest Pair Search (2021)8.09
• Practical And Asymptotically Optimal Quantization Of High-dimensional Vectors In Euclidean Space For Approximate Nearest Neighbor Search (2024)8.82
• Lorann: Low-rank Matrix Factorization For Approximate Nearest Neighbor Search (2024)2.26
• PECANN: Parallel Efficient Clustering With Graph-based Approximate Nearest Neighbor Search (2023)0.00
• Random Binary Trees For Approximate Nearest Neighbour Search In Binary Space (2017)2.26
• Dimensionality-reduction Techniques For Approximate Nearest Neighbor Search: A Survey And Evaluation (2024)0.00