Workshop on Light Fields for Computer Vision

With the availability of commodity light field cameras such as Lytro, Raytrix, and Pelican mobile light field cameras, it has become increasingly common to acquire a light field in place of a single image of the scene. While the original goal of acquiring a light field is to conduct image-based modeling and rendering (e.g., to produce after-capture refocusing), recent studies have shown that light fields can be extremely useful in various applications in computer vision and robotics, including stereo matching and 3D reconstruction, stereoscopy synthesis, saliency detection, surveillance, recognition, etc. There has been also useful and interesting research in several geometrical aspects of light field cameras such as calibration. This workshop aims to stimulate new approaches that use light field acquisition devices and post-processing algorithms for resolving traditionally challenging computer vision problems. It will cover a wide range of topics including new light field sensors, rendering and modeling techniques, camera calibration, and applications in reconstruction, recognition, tracking, and scene understanding.

The workshop is open to ideas from various communities: computational photography, 3D reconstruction, saliency detection, scene understanding, and robotics. It hopes to build on the synergies that have developed among these fields in the recent years. The best workshop paper will be invited to submitted extended versions to appear in a Computer Vision and Image Understanding (CVIU) special issue.

News