Deep Self-Convolutional Activations Descriptor for Dense Cross-Modal Correspondence

TL;DR

DeSCA is a novel, training-free descriptor leveraging deep self-convolutional activations to establish dense correspondences across different imaging modalities with high robustness and efficiency.

Contribution

It introduces a deep self-convolutional architecture based on local self-similarity, improving robustness and discriminative power for cross-modal dense correspondence tasks.

Findings

DeSCA outperforms existing descriptors on challenging cross-modal image pairs.

It is training-free and computationally efficient.

Demonstrates superior robustness to non-rigid deformations.

Abstract

We present a novel descriptor, called deep self-convolutional activations (DeSCA), designed for establishing dense correspondences between images taken under different imaging modalities, such as different spectral ranges or lighting conditions. Motivated by descriptors based on local self-similarity (LSS), we formulate a novel descriptor by leveraging LSS in a deep architecture, leading to better discriminative power and greater robustness to non-rigid image deformations than state-of-the-art cross-modality descriptors. The DeSCA first computes self-convolutions over a local support window for randomly sampled patches, and then builds self-convolution activations by performing an average pooling through a hierarchical formulation within a deep convolutional architecture. Finally, the feature responses on the self-convolution activations are encoded through a spatial pyramid pooling in a circular configuration. In contrast to existing convolutional neural networks (CNNs) based descriptors, the DeSCA is training-free (i.e., randomly sampled patches are utilized as the convolution kernels), is robust to cross-modal imaging, and can be densely computed in an efficient manner that significantly reduces computational redundancy. The state-of-the-art performance of DeSCA on challenging cases of cross-modal image pairs is demonstrated through extensive experiments.