SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03610 · 2022

ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretization

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Efficient detection and description of geometric regions in images is a prerequisite in visual systems for localization and mapping. Such systems still rely on traditional hand-crafted methods for efficient generation of lightweight descriptors, a common limitation of the more powerful neural network models that come with high compute and specific hardware requirements. In this paper, we focus on the adaptations required by detection and description neural networks to enable their use in computationally limited platforms such as robots, mobile, and augmented reality devices. To that end, we investigate and adapt network quantization techniques to accelerate inference and enable its use on compute limited platforms. In addition, we revisit common practices in descriptor quantization and propose the use of a binary descriptor normalization layer, enabling the generation of distinctive binary descriptors with a constant number of ones. ZippyPoint, our efficient quantized network with binary descriptors, improves the network runtime speed, the descriptor matching speed, and the 3D model size, by at least an order of magnitude when compared to full-precision counterparts. These improvements come at a minor performance degradation as evaluated on the tasks of homography estimation, visual localization, and map-free visual relocalization. Code and models are available at https://github.com/menelaoskanakis/ZippyPoint.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.03610")
get_code_for_paper("2203.03610")
have("2203.03610")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.03610.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.03610.svg)](https://syntology.ai/paper/2203.03610)

Connect an agent — have() is free.