LIFE: Lighting Invariant Flow Estimation
This addresses the problem of robust flow estimation for computer vision applications in varying lighting conditions, representing an incremental improvement by combining weak supervision with existing techniques.
The paper tackles the problem of estimating optical flow between images with large lighting variations, where existing methods fail due to lack of annotations, and proposes a weakly supervised framework called LIFE that uses Structure-from-Motion to train a neural network, resulting in outperforming previous methods by large margins in challenging scenarios.
We tackle the problem of estimating flow between two images with large lighting variations. Recent learning-based flow estimation frameworks have shown remarkable performance on image pairs with small displacement and constant illuminations, but cannot work well on cases with large viewpoint change and lighting variations because of the lack of pixel-wise flow annotations for such cases. We observe that via the Structure-from-Motion (SfM) techniques, one can easily estimate relative camera poses between image pairs with large viewpoint change and lighting variations. We propose a novel weakly supervised framework LIFE to train a neural network for estimating accurate lighting-invariant flows between image pairs. Sparse correspondences are conventionally established via feature matching with descriptors encoding local image contents. However, local image contents are inevitably ambiguous and error-prone during the cross-image feature matching process, which hinders downstream tasks. We propose to guide feature matching with the flows predicted by LIFE, which addresses the ambiguous matching by utilizing abundant context information in the image pairs. We show that LIFE outperforms previous flow learning frameworks by large margins in challenging scenarios, consistently improves feature matching, and benefits downstream tasks.