Videos

On this page, you will find a series of videos containing graphics and imaging research from UCL.  Computer graphics conferences usually require a video submission together with the paper, so most of the videos here relate directly to graphics projects.  As such, they are a rather biased sample of our activities!

Overview of UCL Computer Science

Overview of the "Vision and Imaging Science Research Group"

Overview of the "Virtual Environments and Computer Graphics Research Group"

Face Generation Project

The goal of this project was to generate realistic facial images by learning a statistical model of facial appearance. Originally published as

U. Mohammed, S.J.D. Prince and J. Kautz,  “Visio-lisation - Generating Novel Facial Images,” SIGGRAPH,  2009.

Gender Classification

Results of gender classification experiment.  Note that each frame was estimated separately - the results would be even better if we smoothed across frames.  Sometimes, the face detector fails to find the face, which is why the labels flick on and off.  More details concerning this algorithmc can be found in

J. Aghajanian, J. Warrell, S.J.D. Prince, P. Li and J.L. Rohn and B.Baum “Patch-based Within-Object Classification,” International Conference on Computer Vision, 2009.

Capturing a 3D Model

This work used photometric stereo techniques to capture a complex dynamic model.  It was research done by Gabriel Brostow in Cambridge before he joined UCL and can be found in

C. Hernandes, G. Vogiatzis, Gabriel J. Brostow, Bjorn Stenger, Roberto Cipolla, "Non-Rigid Photometric Stereo with Colored Lights", International Conference on Computer Vision, 2007.

Tracking Crowds

Results of tracking crowd motion using Bayesian methods.  This work was done by Gabriel Brostow prior to moving to UCL while he was a research scientist at the University of Cambridge.  Originally published as:

Microrendering for global illumination

Recent approaches to global illumination for dynamic scenes achieve interactive frame rates by using coarse approximations to geometry, lighting, or both, which limits scene complexity and rendering quality. High-quality global illumination renderings of complex scenes are still limited to methods based on ray tracing. While conceptually simple, these techniques are computationally expensive. We present an efficient and scalable method to compute global illumination solutions at interactive rates for complex and dynamic scenes. Our method is based on parallel final gathering running entirely on the GPU. At each final gathering location we perform micro-rendering: we traverse and rasterize a hierarchical point-based scene representation into an importance-warped micro-buffer, which allows for BRDF importance sampling. The final reflected radiance is computed at each gathering location using the micro-buffers and is then stored in image-space. We can trade quality for speed by reducing the sampling rate of the gathering locations in conjunction with bilateral upsampling. We demonstrate the applicability of our method to interactive global illumination, the simulation of multiple indirect bounces, and to final gathering from photon maps. Originally pubilshed as:  

T. Ritschel, T. Engelhardt, T. Grosch, H.-P. Seidel, J. Kautz, C. Dachsbacher, "Micro-Rendering for Scalable, Parallel Final Gathering," ACM Transactions on Graphics (Proceedings SIGGRAPH Asia 2009) 28(5), December 2009, pages 132:1-132:8

Consistent Scene Illumination Using a Chromatic Flash

Flash photography is commonly used in low-light conditions to prevent noise and blurring artifacts. However, flash photography commonly leads to a mismatch between scene illumination and flash illumination, due to the bluish light that flashes emit. Not only does this change the atmosphere of the original scene illumination, it also makes it difficult to perform white balancing because of the illumination differences. Professional photographers sometimes apply colored gel filters to the flashes in order to match the color temperature. While effective, this is impractical for the casual photographer. We propose a simple but powerful method to automatically match the correlated color temperature of the auxiliary flash light with that of scene illuminations allowing for well-lit photographs while maintaining the atmosphere of the scene. Our technique consists of two main components. We first estimate the correlated color temperature of the scene, e.g., during image preview. We then adjust the color temperature of the flash to the scene's correlated color temperature, which we achieve by placing a small trichromatic LCD in front of the flash. We demonstrate the effectiveness of this approach with a variety of examples.  Originally published as:

M. H. Kim, J. Kautz, "Consistent Scene Illumination Using a Chromatic Flash" Computational Aesthetics in Graphics, Visualization, and Imaging