Fatma Güney

Learn More
Stereo techniques have witnessed tremendous progress over the last decades, yet some aspects of the problem still remain challenging today. Striking examples are reflecting and textureless surfaces which cannot easily be recovered using traditional local regularizers. In this paper, we therefore propose to regularize over larger distances using(More)
Motivated by the success of deep learning techniques in matching problems, we present a method for learning context-aware features for solving optical flow using discrete optimization. Towards this goal, we present an efficient way of training a context network with a large receptive field size on top of a local network using dilated convolutions on(More)
Despite recent progress, reconstructing outdoor scenes in 3D from movable platforms remains a highly difficult endeavour. Challenges include low frame rates, occlusions, large distortions and difficult lighting conditions. In this paper, we leverage the fact that the larger the reconstructed area, the more likely objects of similar type and shape will occur(More)
Recent years have witnessed amazing progress in AI related fields such as computer vision, machine learning and autonomous vehicles. As with any rapidly growing field, however, it becomes increasingly difficult to stay up-to-date or enter the field as a beginner. While several topic specific survey papers have been written, to date no general survey on(More)
Existing optical flow datasets are limited in size and variability due to the difficulty of capturing dense ground truth. In this paper, we tackle this problem by tracking pixels through densely sampled space-time volumes recorded with a high-speed video camera. Our model exploits the linearity of small motions and reasons about occlusions from multiple(More)
This work introduces a real-time video-based open-set face recognition system. The system has been developed for the identification of people who stand in front of an interactive screen to communicate with a virtual application. The system uses Discrete Cosine Transform (DCT) features obtained from non-overlapping 20 blocks, and Support Vector Machines(More)
In this supplementary document, we first present additional experiments to show the convergence of training in Section 1.1 and compare the performance of exact matching against a frequently used approximate nearest neighbour search library in Section 1.2. We then show the speed-ups we gain by the strided implementation of the patch-based dilated(More)
Reinke’s edema is one of the benign mucosal diseases of the vocal cord, it develops as a result of the accumulation of gelatinous edematous fluid in superficial lamina propria of vocal folds (Reinke’s space). This fluid accumulates in this region because of local impairment of lymphatic circulation or vascular congestion and stasis secondary to damage of(More)