Video before: dead, linear, one-size-fits all Video now: interactive, responsive, truly personalized Wdyt? 👀

Check out MultiDiff #CVPR2024! From a single RGB image, MultiDiff enables scene-level novel view synthesis with free camera control. sirwyver.github.io/MultiDiff youtu.be/SKpFFtVJo9c Great work by @normanisation Katja Schwarz Barbara Roessle, L Porzi, S Rota Bulò, P Kontschieder

Exciting to see computer vision in action during the #EURO Football Championship! Not much info online but apparently: 500 fps IMU inside the ball synced w/ 12x 50fps cameras -> tracks 29 body points & fits skeleton and 3d body model. Also, clear offside by Delaney - no goal :)

Got unfortunate news from #ECCV2024 (and waited too long to load the paper id list)? Consider sending the (slightly revised) version of your paper including the reviews to the GCPR fast track and present in Munich in September already!

📢 SIGGRAPH Asia reviews are out 📢

According to google scholar, #CVPR is now the second-most influential academic venue, right behind Nature. #ICCV is ranked 13th. This is a great success for our community, but I also see it skeptical as large numbers don't quite reflect research quality. scholar.google.com/citations?view…

Onsite situation in the #Euro Championship final, right before Oyarzabal scores the 2:1 lead for Spain. Again, great to see computer vision tech in action :) Clearly onsite, and congrats to #Spain for winning the #Euro. Well deserved!

Excited to present DiffCAD coming to #SIGGRAPH2024! Daoyi Gao introduces the first probabilistic single-view CAD retrieval & alignment. We train only on synthetic -> generalize robustly to real images! Check out the code: daoyig.github.io/DiffCAD_/ w/David Rozenberszki, Stefan Leutenegger

New this year at GCPR and VMV: Research Spotlights! We are committed to supporting early career researchers by offering oral presentation slots to outstanding senior PhD students or postdocs to showcase their research journey so far and gain visibility.

Unfortunately, I won't make it to #SIGGRAPH this year 😢 It's an excellent technical program though, and I'm sure it's going to be a fantastic conference. Please share cool papers and social events :)

#GCPR'24 and #VMV'24 will be held in Munich from September 10-13th! We have a fantastic set of keynote speakers and invited PI talks - check it out! gcpr-vmv.de/year/2024 Also the registration is open: early bird until **August 12th** - join us for an amazing event :)

The #GCPR-#VMV'2024 conference program is online, featuring cutting-edge topics across computer vision, graphics, and visualization! The conference will take place Sept 10-13th in Munich. 𝐃𝐨𝐧'𝐭 𝐟𝐨𝐫𝐠𝐞𝐭 𝐭𝐨 𝐫𝐞𝐠𝐢𝐬𝐭𝐞𝐫 & 𝐣𝐨𝐢𝐧 𝐮𝐬 :) gcpr-vmv.de/year/2024/prog…

Nearly half of Nvidia's revenue comes from just four customers ($13.8 bn out of $30 bn). Presumably, that's Amazon, Google, Microsoft, and Meta. Or in other words: these companies own almost half of all modern GPUs, forming an oligopoly of #AI compute. fortune.com/2024/08/29/nvi…

The complete GCPR-VMV program is now online and it is still not too late to join us! We have tutorials on Virtual Humans, Quantum-Enhanced Vision and 3D Shape Analysis, as well as four keynote talks, four PI-Talks and three research spotlights from junior researchers.

Check out "Robust 3D Gaussian Splatting"! We improve NVS quality by removing artifacts from dynamic objects through object-aware segmentation masks. paulungermann.github.io/Robust3DGaussi… Great work by our stellar MA student Paul Ungermann A. Ettenhofer advised by Barbara Roessle. #GCPR24

🚀 Ready to showcase your groundbreaking work? Submit your research to Eurographics 2025 and join us in London to shape the future of computer graphics 🌍✨ Deadline Oct 3, 2024: eg25.cs.ucl.ac.uk/main/callforfu…

G3DST: Generalizing 3D Style Transfer with NeRF across Scenes and Styles! Given a style latent, our hypernetwork estimates MLP params that transform aggregated ray features. mericadil.github.io/G3DST/ Great work by our MA student adil meric U. Kocasari Barbara Roessle #GCPR24