DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning
Authors:
- 16 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 20278-20287
Abstract
Two-view correspondence learning has recently focused on considering the coherence and smoothness of the motion field between an image pair. Dominant schemes include controlling the complexity of the field function with regularization or smoothing the field with local filters, but the former suffers from heavy computational burden, and the latter fails to accommodate discontinuities in the case of large scene disparities. In this paper, inspired by Fourier expansion, we propose a novel network called DeMatch, which decomposes the motion field to retain its main “low-frequency” and smooth part. This achieves implicit regularization with lower computational cost and generates piece-wise smoothness naturally. Specifically, we first decompose the rough motion field that is contaminated by false matches into several different sub-fields, which are highly smooth and contain the main energy of the original field. Then, with these smooth sub-fields, we recover a cleaner motion field from which correct motion vectors are subsequently derived. We also design a special masked decomposition strategy to further mitigate the negative influence of false matches. All the mentioned processes are finally implemented in a discrete and learnable manner, avoiding the difficulty of calculating real dense fields. Extensive experiments reveal that DeMatch outperforms state-of-the-art methods in multiple tasks and shows promising low computational usage and piecewise smoothness property. The code and trained models are publicly available at https://github.com/SuhZhang/DeMatch.Keywords
This publication has 36 references indexed in Scilit:
- Image Matching from Handcrafted to Deep Features: A SurveyInternational Journal of Computer Vision, 2020
- Locality Preserving MatchingInternational Journal of Computer Vision, 2018
- Structure-from-Motion Revisited2016
- Three things everyone should know to improve object retrieval2012
- Multi-output learning via spectral filteringMachine Learning, 2012
- Modeling the World from Internet Photo CollectionsInternational Journal of Computer Vision, 2007
- Automatic Panoramic Image Stitching using Invariant FeaturesInternational Journal of Computer Vision, 2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Multiple View Geometry in Computer Vision2004
- Finite-Dimensional Vector Spaces1974