TopicFM: Robust and Interpretable Topic-Assisted Feature Matching

TL;DR

TopicFM introduces a novel image-matching approach using topic modeling to encode high-level semantic contexts, enhancing robustness and interpretability in challenging scenes with large variations or minimal textures.

Contribution

It is the first to apply topic modeling for explicit high-level context encoding in image matching, improving robustness and providing interpretability.

Findings

Outperforms state-of-the-art methods on outdoor and indoor datasets.

Shows significant robustness in challenging scenes with large variations.

Provides explainable matching results through inferred topics.

Abstract

This study addresses an image-matching problem in challenging cases, such as large scene variations or textureless scenes. To gain robustness to such situations, most previous studies have attempted to encode the global contexts of a scene via graph neural networks or transformers. However, these contexts do not explicitly represent high-level contextual information, such as structural shapes or semantic instances; therefore, the encoded features are still not sufficiently discriminative in challenging scenes. We propose a novel image-matching method that applies a topic-modeling strategy to encode high-level contexts in images. The proposed method trains latent semantic instances called topics. It explicitly models an image as a multinomial distribution of topics, and then performs probabilistic feature matching. This approach improves the robustness of matching by focusing on the same semantic areas between the images. In addition, the inferred topics provide interpretability for matching the results, making our method explainable. Extensive experiments on outdoor and indoor datasets show that our method outperforms other state-of-the-art methods, particularly in challenging cases. The code is available at https://github.com/TruongKhang/TopicFM.