João received his M.Sc in Computer Science from the University of British Columbia. During his Computer Science Major at University of Coimbra, he worked at the Computer Animation and Interaction Capture Lab, McGill University. Outside of academia, João is primarily known for being the developer of third party software for World of Warcraft with millions of downloads worldwide.
Publications
Cost Volume Refinement for Depth Prediction
Light-field cameras are becoming more popular in the consumer market. Their data redundancy allows, in theory, to accurately refocus images after acquisition and to predict the depth of each point visible from the camera. Combined, these two features allow for the generation of full-focus images, which is impossible in traditional cameras. Multiple methods for depth prediction from light fields (or stereo) have been proposed over the years. A large subset of these methods relies on cost-volume estimates 3D objects where each layer represents a heuristic of whether each point in the image is at a certain distance from the camera. Generally, this volume is used to regress a depth map, which is then refined for better results. In this paper, we argue that refining the cost volumes is superior to refining the depth maps in order to further increase the accuracy of depth predictions. We propose a set of cost-volume refinement algorithms and show their effectiveness.
- Date: 10/01/2021
- //
- Featured In: 25th International Conference on Pattern Recognition (ICPR) Milan, Italy
- //
- Publication Type: Conference Papers
- //
- Author(s): João L. Cardoso, Nuno Gonçalves and Michael Wimmer
- //
- DOI: 10.1109/ICPR48806.2021.9412730
- //
- Download File
- //
- Visit Website