GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs

TL;DR

GIFT introduces a novel group convolution-based descriptor that achieves both high discriminability and invariance to geometric transformations, improving local image correspondence tasks.

Contribution

It proposes a new descriptor using group convolutions to maintain discriminability while ensuring invariance to transformations, unlike traditional pooling methods.

Findings

GIFT outperforms existing descriptors on benchmark datasets.

It significantly improves relative pose estimation accuracy.

The method is theoretically provably invariant to transformation groups.

Abstract

Finding local correspondences between images with different viewpoints requires local descriptors that are robust against geometric transformations. An approach for transformation invariance is to integrate out the transformations by pooling the features extracted from transformed versions of an image. However, the feature pooling may sacrifice the distinctiveness of the resulting descriptors. In this paper, we introduce a novel visual descriptor named Group Invariant Feature Transform (GIFT), which is both discriminative and robust to geometric transformations. The key idea is that the features extracted from the transformed versions of an image can be viewed as a function defined on the group of the transformations. Instead of feature pooling, we use group convolutions to exploit underlying structures of the extracted features on the group, resulting in descriptors that are both discriminative and provably invariant to the group of transformations. Extensive experiments show that GIFT outperforms state-of-the-art methods on several benchmark datasets and practically improves the performance of relative pose estimation.