GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs
This addresses the need for robust local descriptors in computer vision for tasks like image matching, with incremental improvements in invariance and distinctiveness.
The paper tackles the problem of finding local correspondences between images with different viewpoints by introducing GIFT, a visual descriptor that is both discriminative and robust to geometric transformations, outperforming state-of-the-art methods on benchmark datasets and improving relative pose estimation.
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.