The Visual Computing Group, led by Hanspeter Pfister, explores and provides visual analysis tools and methods to help scientists and researchers better process and understand large, multi-dimensional data sets in various domains such as neuroscience, genomics, systems biology, astronomy, and medicine.
Projects
Latest Publications
-
Discrete Cosine Transform Network for Guided Depth Map Super-Resolution
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). -
MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. -
Texture-based Error Analysis for Image Super-Resolution
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition ("Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition"). -
A Survey of Visualization and Analysis in High-Resolution Connectomics
Computer Graphics Forum (EuroVis). -
Barrio: Customizable Spatial Neighborhood Analysis and Comparison for Nanoscale Brain Structures
Computer Graphics Forum (Proceedings Eurographics/IEEE Symposium on Visualization, Eurovis 2022).
News
-
Harvard VCG
@HarvardVCGRT @jakobtroidl: 🎊 Yeahi! Our survey paper on visualization and analysis in high-resolution connectomics 🧠 got accepted for presentation @E… -
Harvard VCG
@HarvardVCGNew work from our group on out-of-distribution generalization in multi-task learning is now out in Nature Machine I… Humans easily recognize new objects in unseen poses, but can CNNs? Our work in Nature Machine Intelligence explores… @spandan_madan -
Harvard VCG
@HarvardVCGRT @robertK_vis: Our new IEEE VIS/TVCG paper "Scope2Screen: Focus+Context Techniques for Pathology Tumor Assessment in Multivariate Image D… -
Harvard VCG
@HarvardVCGRT @hen_str: Our preprint on Human-AI Collaboration for Data-Backed Text generation now available. Presentation next week at @ieeevis confe… -
Harvard VCG
@HarvardVCGRT @spandan_madan: New preprint! We show that CNNs and Transformers are brittle to small changes in 3D perspective and lighting. We propose…