Our team will be presenting (oral) at BMVC 2018 on the topic of semantic image segmentation, optical flow and normal estimation. Congratulations to our team members on this great achievement and thank for all the hard work in the past months! Together we keep pushing the boundaries of computer vision technologies and research.
Abstract. Optical flow, semantic segmentation, and surface normals represent different information modalities, yet together they bring better cues for scene understanding problems.
In this paper, we study the influence between the three modalities: how one impacts on
the others and their efficiency in combination. We employ a modular approach using
a convolutional refinement network which is trained supervised but isolated from RGB
images to enforce joint modality features. To assist the training process, we create a
large-scale synthetic outdoor dataset that supports dense annotation of semantic segmentation, optical flow, and surface normals. The experimental results show positive influence among the three modalities, especially for objects’ boundaries, region consistency,
and scene structures.
