Gao_HOMO-Feature_Cross-Arbitrary-Modal_Image_Matching_with_Homomorphism_of_Organized_Major_Orientation@ICCV2025@CVF

Total: 1

#1 HOMO-Feature: Cross-Arbitrary-Modal Image Matching with Homomorphism of Organized Major Orientation [PDF] [Copy] [Kimi] [REL]

Authors: Chenzhong Gao, Wei Li, Desheng Weng

An exploration of cross-arbitrary-modal image invariant feature extraction and matching is made, with a purely handcrafted full-chain algorithm, Homomorphism of Organized Major Orientation (HOMO), being proposed. Instead of using deep models to conduct data-driven black-box learning, we introduce a Major Orientation Map (MOM), effectively combating image modal differences. Considering rotation, scale, and texture diversities in cross-modal images, HOMO incorporates a novel, universally designed Generalized-Polar descriptor (GPolar) and a Multi-scale Strategy (MsS) to gain well-rounded capacities. HOMO achieves the best comprehensive performance in feature matching on several generally cross-modal datasets, challenging compared with a set of state-of-the-art methods including 7 traditional algorithms and 10 deep network models. A dataset named General Cross-modal Zone (GCZ) is proposed, which shows practical values. Codes with datasets are available at https://github.com/MrPingQi/HOMO_Feature_ImgMatching.

Subject: ICCV.2025 - Poster