Low Bit-rate 3D feature descriptors for depth data from Kinect-style sensors

作者：

Highlights：

• We employ lattice quantization to effciently compress 3D feature descriptors.

• They can be directly matched in compressed domain. Hence drastically reducing the memory footprint and computational requirements.

• We propose double stage lattice quantization to compress SHOT descriptor even more.

• Three state-of-the-art descriptors are compressed and their performance is reported.

摘要

Highlights•We employ lattice quantization to effciently compress 3D feature descriptors.•They can be directly matched in compressed domain. Hence drastically reducing the memory footprint and computational requirements.•We propose double stage lattice quantization to compress SHOT descriptor even more.•Three state-of-the-art descriptors are compressed and their performance is reported.

论文关键词：3D feature descriptors,Compression,Lattice quantization,3D keypoint matching

论文评审过程：Received 30 August 2016, Revised 23 November 2016, Accepted 24 November 2016, Available online 27 November 2016, Version of Record 19 December 2016.

论文官网地址：https://doi.org/10.1016/j.image.2016.11.004