Computational Sciences Group @KAUST_News headed by Prof. Dominik L. Michels #Algorithm #ArtificialIntelligence #ScientificComputing #Simulation #VisualComputing
KAUST
Joined November 2020
- Tweets131
- Following56
- Followers798
- Likes199
🌳 How do you plant a city park for shade, quiet and beauty, all at once?
Our new paper #GreenScapes, to appear at #SIGGRAPHAsia2026, pairs a vision-language model with CMA-ES optimization to design 3D urban vegetation, from flower beds to trees. It balances shade, acoustic screening and aesthetics.
🔗 greenscapes-project.github.i…
#ComputerGraphics #UrbanPlanning #AI
Our work on #DeepHadad – AI-based restoration of damaged ancient inscriptions using synthetic erosion data – has been highlighted in Communications of the ACM (@CACMmag).
📄 Paper (ACM JOCCH): doi.org/10.1145/3727623
📰 Article: cacm.acm.org/news/ai-helps-s…
#AI #DigitalHumanities #CulturalHeritage #KAUST
Excited to share that our paper '#Woodstock: Interactive Modeling of Fungal Wood Decay' has been accepted to #SIGGRAPH2026 (ACM TOG)!
We present a #simulator for the complex biophysical process of #wood decay capturing #fungal colonization, chemical defense, moisture dynamics, and structural failure in a unified volumetric framework.
Project page: jango6324.github.io/woodstoc…
🌳🍄
Excited to see our #SIGGRAPH Asia 2025 paper "Fire-X: Extinguishing #Fire with Stoichiometric Heat Release" featured as the cover image of ACM Transactions on Graphics!
Check out Fire-X to simulate fire across solids, liquids, and gase.
Project Page: helgewrede.github.io/firex/
KAUST Computational Sciences retweeted
Join us in celebrating the 2024–2025 Dean's List honorees from the @KAUST_CEMSE Division.
These students have gone above and beyond, demonstrating the exceptional drive, curiosity and perseverance that define our community. Earning this distinction is a testament to their passion, hard work and commitment to academic excellence.
Their distinction is not only a personal milestone but also a reflection of the vibrant academic environment we cultivate—one that encourages curiosity, innovation and continuous growth.
Congratulations to all honorees for this well-deserved recognition. You make our community proud!
#KAUST #CEMSE #DeansList #AcademicExcellence #HigherEducation #STEM #StudentSuccess
Excited to share our #ICCV25 paper presenting an Augmented Mass-Spring (AMS) model for real-time dense #HairSimulation!
AMS adds biphasic coupling to traditional mass-spring systems → better stability, global preservation and non-Hookean effects — efficiently.
@KAUST_News @Adobe
Our #FlameForge simulator for #Wood #Combustion presented at @SympCompAnim 2025 is featured as the cover image of the 'Proceedings of the ACM on #ComputerGraphics and Interactive Techniques'. @KaustResearch
KAUST Computational Sciences retweeted
📢 #ICLR2025 I'll be presenting our spotlight paper "Perm: A Parametric Representation for Multi-Style 3D Hair Modeling". Swing by and let's talk about hair! #Adobe #AdobeResearch #Yale
⏰ Friday, April 25 | 10am - 12:30pm SGT
📍 Hall 3 | Poster #90
🔗 cs.yale.edu/homes/che/projec…
Excited to share #Harmony: A joint self-supervised and weakly-supervised method learning generalized visual features from web-scraped data. It outperforms #CLIP/#SigLIP/MaskCLIP/SLIP/iBOT/MAE on classification/segmentation/detection.
arxiv.org/abs/2405.14239
@KAUST_News @Harvard
Ph.D. candidate Alejandro Amador @agrozamad discussed how our work @siggraph contributes to the advancement of climatology.
blog.siggraph.org/2025/02/ad…
KAUST Computational Sciences retweeted
Here’s our state-of-the-art hair simulator in action! It seamlessly handles complex hair-object interactions in real time, ensuring stability and enhanced realism. 💈✨
Want to give it a try? It’s open source! 🎉 Dive in: agrosamad.github.io/AMS/
#HairSimulation #DigitalHair
KAUST Computational Sciences retweeted
We have designed a cutting edge hair simulator for animating thousands of strands in real time, enabling dynamic editing and interactions with breathtaking details! Oh, and it’s open source! 💇♀️📷 Check it out: agrosamad.github.io/AMS/
#AdobeResearch #HairSimulation #3DModeling
KAUST Computational Sciences retweeted
Looking for the perfect hairstyle for the upcoming holidays?🎄✨ Join us this Friday at Real-Time Live! for our demo Digital Salon, an interactive hair grooming and simulation tool (Friday 4pm, Hall C 4F). Swing by if you’re interested! #SIGGRAPHAsia2024 #AdobeResearch #Adobe
KAUST Computational Sciences retweeted
200,000 Trees Are Lit On Fire! (Simulation)
youtu.be/ANFKHtqBqjQ
KAUST Computational Sciences retweeted
🎥 Watch the Real-Time Live! trailer for an exclusive look at the most cutting-edge real-time graphics hitting the stage at SIGGRAPH Asia 2024! Witness live demos that redefine innovation.
Real-Time Live! Chair: Takahito Tejima (@gishicho)
🎟️bit.ly/sa24reg
#CG #Tech
Happy to announce the code release of #DigitalSalon: Our AI and Physics-Driven #RealTime 3D #HairSimulation and Grooming tool @SIGGRAPHAsia 2024. Step-by-step instructions and example scenes are provided.
Project and Code: digital-salon.github.io/
@Adobe @KAUST_News @MPI_IS @Yale
KAUST Computational Sciences retweeted
🚀 Debut "Digital Salon: An AI and Physics-Driven Tool for 3D Hair Grooming and Simulation"! Generate detailed hairstyles, combine text-based creation, interactive editing, and AI rendering—all in one. With real-time simulation of 10,000 to 80,000 strands on an NVIDIA Laptop GPU, Digital Salon streamlines advanced hair design for everyone. Explore it here: digital-salon.github.io #AI #3DModeling #HairSimulation #DigitalArt #DigitalHuman #Adobe #NVIDIA
KAUST Computational Sciences retweeted
Along with Perm, we release Hair20K—a large-scale public 3D hairstyle database featuring strand-based hair models! Dive into the dataset and explore its potential for your projects! Check it out here: zhouyisjtu.github.io/project… #3DModeling #HairRendering #ComputerGraphics #OpenSource #DigitalHair #DigitalHuman
KAUST Computational Sciences retweeted
Sharing "Perm: A Parametric Representation for Multi-Style 3D Hair Modeling"! Aiming to be the SMPL for 3D hair, it has disentangled parameters to control hair cut types and curl patterns, a generic prior for single-view reconstruction and hair-conditioned image generation. We've released the code, the trained model on 20k public hair data, and by popular demand, the data itself! cs.yale.edu/homes/che/projec… #AdobeFirefly #3DModeling #DigitalHair
Our paper #Scintilla on simulating combustible vegetation for #Wildfires is available now! 🌲🔥
Discover our novel simulator at #SIGGRAPH 2024.
#EnvironmentalScience @KaustResearch
Paper: storage.googleapis.com/pirk.…
