If-net: An Illumination-invariant Feature Network

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

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keychen2020if

Related papers

• Mifnet: Learning Modality-invariant Features For Generalizable Multimodal Image Matching (2025)8.90
• DCI: Discriminative And Contrast Invertible Descriptor (2018)0.00
• No Fear Of The Dark: Image Retrieval Under Varying Illumination Conditions (2019)10.74
• Tasks Integrated Networks: Joint Detection And Retrieval For Image Search (2020)11.08
• GLARE: Low Light Image Enhancement Via Generative Latent Feature Based Codebook Retrieval (2024)16.37
• Learning Condition Invariant Features For Retrieval-based Localization From 1M Images (2020)0.00
• Retrieval-based Localization Based On Domain-invariant Feature Learning Under Changing Environments (2019)9.92
• Same Features, Different Day: Weakly Supervised Feature Learning For Seasonal Invariance (2020)11.92