IF-Net: An Illumination-invariant Feature Network

TL;DR

IF-Net is a novel feature descriptor network designed to be robust against illumination variations, improving matching accuracy and visual localization performance in challenging lighting conditions.

Contribution

The paper introduces a new training scheme, ROI loss, and hard-positive mining to enhance illumination-invariant feature descriptors, outperforming existing methods.

Findings

Achieves state-of-the-art results on public patch matching benchmarks.

Demonstrates superior performance in visual localization under large illumination changes.

Proves effectiveness of proposed training strategies for illumination invariance.

Abstract

Feature descriptor matching is a critical step is many computer vision applications such as image stitching, image retrieval and visual localization. However, it is often affected by many practical factors which will degrade its performance. Among these factors, illumination variations are the most influential one, and especially no previous descriptor learning works focus on dealing with this problem. In this paper, we propose IF-Net, aimed to generate a robust and generic descriptor under crucial illumination changes conditions. We find out not only the kind of training data important but also the order it is presented. To this end, we investigate several dataset scheduling methods and propose a separation training scheme to improve the matching accuracy. Further, we propose a ROI loss and hard-positive mining strategy along with the training scheme, which can strengthen the ability of generated descriptor dealing with large illumination change conditions. We evaluate our approach on public patch matching benchmark and achieve the best results compared with several state-of-the-arts methods. To show the practicality, we further evaluate IF-Net on the task of visual localization under large illumination changes scenes, and achieves the best localization accuracy.