CVJan 16, 2018

Deep Multi-Spectral Registration Using Invariant Descriptor Learning

arXiv:1801.05171v613 citations
Originality Incremental advance
AI Analysis

This addresses a challenging multi-modal image registration problem for applications like remote sensing or medical imaging, but it is incremental as it builds on existing feature-based and deep-learning techniques.

The paper tackles the problem of aligning cross-spectral images, specifically visible to near-infrared registration, by introducing a deep-learning method that uses a learned invariant descriptor, achieving sub-pixel accuracy and outperforming existing methods.

In this paper, we introduce a novel deep-learning method to align cross-spectral images. Our approach relies on a learned descriptor which is invariant to different spectra. Multi-modal images of the same scene capture different signals and therefore their registration is challenging and it is not solved by classic approaches. To that end, we developed a feature-based approach that solves the visible (VIS) to Near-Infra-Red (NIR) registration problem. Our algorithm detects corners by Harris and matches them by a patch-metric learned on top of CIFAR-10 network descriptor. As our experiments demonstrate we achieve a high-quality alignment of cross-spectral images with a sub-pixel accuracy. Comparing to other existing methods, our approach is more accurate in the task of VIS to NIR registration.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes