Supervisors: Dr. Martin Danelljan, Dr. Radu Timofte, Prof. Luc Van Gool
The modern approaches for computer vision tasks significantly rely on machine learning, which requires a large number of quality images. While there is a plethora of image datasets with a single type of images, there is a lack of datasets collected from the multiple cameras. In this thesis, we introduce a Paired Image, and Video data from three CAMeraS, namely PIV3CAMS, aiming for multiple computer vision tasks. The PIV3CAMS dataset consists of 8385 pairs of images and 82 pairs of videos taken from three different cameras: Canon D5 Mark IV, Huawei P20, and ZED stereo camera. The dataset includes various indoor and outdoor scenes from different locations of Zurich(Switzerland), and Cheonan (South Korea). Some of the computer vision applications that can benefit from PIV3CAMS dataset are image/video enhancement, view interpolation, image matching, and much more. We provide a careful explanation of the data collection process and details analysis of the data. The second part of this thesis studies the usage of depth information on view synthesizing task. In addition to the regeneration of a current state-of-the-art algorithm, we investigate several proposed alternative models that integrate depth information geometrically. Through extensive experiments, we show that the effect of depth is crucial in small view changes. Finally, we apply our model to the introduced PIV3CAMS dataset to synthesize novel target views as an example application of PIV3CAMS.