Computer Vision
Enabling computers and devices to understand what they see.
Video
World first Time-of-flight RGB-Depth camera (1998)
I was working between 1996-2003 at 3DV System, where we developed the world first RGBD Time of flight (TOF) camera. It was an add-on to a broadcast TV camera that generated a 30Hz full frame…
Video
Modeling Hair from Multi View – Video
Modeling Hair from Multi Views Yichen Wei, Eyal Ofek, Long Quan and Harry Shum. MSR-TR-2005-191 | January 2005, ACM SIGGRAPH 2005 In this paper, we propose a novel image-based approach to model hair geometry from…
Tool
VL-BERT
VL-BERT is a simple yet powerful pre-trainable generic representation for visual-linguistic tasks. It is pre-trained on the massive-scale caption dataset and text-only corpus, and can be fine-tuned for various down-stream visual-linguistic tasks, such as Visual…
Video
Webinar: Designing Computer Vision Algorithms to Describe the Visual World to People Who Are Blind or Low Vision
A common goal in computer vision research is to build machines that can replicate the human vision system (for example, detect an object or scene category, describe an object or scene, or locate an object).…
Project
ImagePairs
Super Resolution is the problem of recovering a high-resolution image from a single or multiple low-resolution images of the same scene. It is an ill-posed problem since high frequency visual details of the scene are…
Video
Modeling Hair from Multi Views – SIGGRAPH 2005 Talk
Presenting the paper ‘Modeling Hair from Multi Views’ / Y. Wei, E. Ofek, L. Quan & H. Shum at SIGGRAPH 2005. ABSTRACT In this paper, we propose a novel image-based approach to model hair geometry…
Publication
The GeoLifeCLEF 2020 Dataset
Publication