The Visual Computing Group (VCG) at Harvard performs research in the areas of visualization, computer The group is led by Professor Hanspeter Pfister.
The Visual Computing Group (VCG) at Harvard performs research in the areas of visualization, computer graphics, and computer vision.
04/21/2021
Another wonderful news- Virtual toast to our Dr. Lekschas! 🍾 Visual Computing Group
Harvard VCG on Twitter “🎉Congratulations to for passing his PhD defense with flying colors! Virtual toast to Dr. Lekschas 🍾 ”
04/19/2021
Congratulations! Virtual toast to our Dr. Matejek 🍾 Visual Computing Group
Harvard VCG on Twitter “🎉Congratulations to for successfully defending his PhD work! Virtual toast to our Dr. Matejek 🍾 ”
12/03/2019
Our vis group talked about bringing AR cloud to sports, or SportsXR, to augment fans, athletes and coaches experiences with computational power.
Check out the full article on HBS digital initiative!
Bringing the AR cloud to sports - Harvard Business School Digital Initiative As you settle into your seat to watch the NBA action on the court below, you take a sip of your beverage and gaze through your augmented reality (AR) device. Players’ names and box scores appear and you watch replays on demand. When your favorite player makes a highlight-reel move, you share the p...
09/09/2019
Summer retreat by the lake got us all excited and we are getting ready for the new semester!
05/31/2019
Yesterday was the last step for our own Daniel Haehn and Nam Wook Kim in becoming PhD graduates! 🎉Huuuge congrats! You were marvelous Harvard John A. Paulson School of Engineering and Applied Sciences students and we know you will be fabulous Professors. We're sad to see you go but soo happy and excited for what's to come!
02/27/2019
Many greetings from our annual ski retreat!
09/26/2018
See you in a month at the IEEE Vis conference in Berlin! VCG papers will be presented Wednesday and Thursday!
Please visit our website for more information and paper copies: https://vcg.seas.harvard.edu/
09/13/2018
The fabulous Felix Gonda just presented our work on 'Parallel Separable 3D Convolution for Video and Volumetric Data Understanding' at BMVC! Find the paper/presentation/poster here: https://vcg.seas.harvard.edu/publications/parallel-separable-3d-convolution-for-video-and-volumetric-data-understanding
We replace 3D convolution layers, common in modern network architectures, with the multiple 2D convolution layers and achieve slimmer models and better performance!
09/06/2018
Are machines ready for graphical perception? We replicate Cleveland and McGill's seminal experiments using CNNs. This includes experiments of bar charts versus pie charts and measures of cross-network generalizability.
Video/Code/Data at https://bit.ly/machineperception
Convolutional neural networks can successfully perform many computer vision tasks on images. For visualization, how do CNNs perform when applied to graphical perception tasks? We investigate this question by reproducing Cleveland and McGill’s seminal 1984 experiments, which measured human perception efficiency of different visual encodings and defined elementary perceptual tasks for visualization. We measure the graphical perceptual capabilities of four network architectures on five different visualization tasks and compare to existing and new human performance baselines. While under limited circumstances CNNs are able to meet or outperform human task performance, we find that CNNs are not currently a good model for human graphical perception. We present the results of these experiments to foster the understanding of how CNNs succeed and fail when applied to data visualizations.
https://danielhaehn.com/papers/?haehn2018evaluating
08/28/2018
Our annual retreat at beautiful Rolling Ridge! Lots of work and even more fun!
07/19/2018
Retweeted Daniel Haehn ():
Great milestone! Congrats!! 🍾🥇
HHMI NEWS on Twitter “HHMI News: Scientists at have taken detailed pictures of the entire brain of a fruit fly using transmission electron microscopy. https://t.co/YU5XndNPBj”