Our QCVML workshop European Conference on Computer Vision #ECCV2026 is once again a demonstration of the openness of our #CVPR / #CVML community to novel directions in #computervision and #machinelearning. qcvml.github.io #ECCV2024

This is Cam, the Corgi Executive Officer. She is @Corgi.cam, and she is presenting an #ECCV2024 demo on AI3D Sculpt on Wednesday at 9 am.

A great moment for CS and ML! Hopfield networks significantly influenced the field. The official statement by the Nobel Committee is that ANNs are actively used nowadays in many areas of physics (such as the development of materials with new characteristics).

It was great to talk and connect with other speakers, organisers and students at #EQAI2024. The program covered a broad spectrum of topics in quantum computing theory and practical aspects (eqai.eu/speakers/). Stay tuned for next year's European Summer School on Quantum AI!

Join our #CVPR2025 presentations next week in Nashville on: • Monocular non-rigid 3D surface tracking • Solving composite and binary parametrised problems on quantum annealers (Highlight) • Shape correspondence estimation • 3D synthesis of bimanual interactions

🎬 It’s #CVPR2025 season! Meet Thin-Shell-SfT — we enable fine-grained, monocular non-rigid 3D surface tracking with: ✅ Continuous and adaptive deformation fields ✅ Continuous thin-shell physics prior ✅ Surface-induced 3D Gaussian splatting 🧵(1/2)

Exciting News! Campus Saarbrücken could become a new hub for quantum⚛️algorithm and hardware research! 4DQV/MPI already collaborates with Saarland University on, e.g., Quantum-enhanced Computer Vision. What is your quantum domain? Article (in German): sr.de/sr/home/nachri…

#CVPR2025 Workshop on Event-based Vision covers various topics, including the applications of event cameras in XR (e.g. eye tracking on head-mounted devices enabling foveated rendering). I am giving a talk today on Event-based Non-rigid 3D Reconstruction and Novel-View Synthesis.

QuCOOP, #CVPR2025 Highlight! We extend the scope of Adiabatic Quantum Computing to composite and binary-parametrised, possibly non-quadratic problems. QuCOOP iteratively approximates the original objective function by local QUBO forms. One example application is shape matching.

Do not miss Dynamic Neural Point Clouds, our #EUROGRAPHICS2025 full paper that lifts monocular non-rigid view synthesis to a new level by combining fast optimisation, real-time frame rates and highly competitive rendering quality. arxiv.org/pdf/2406.10078 github.com/MoritzKappel/D…

{1/8} 🧵 When you click a link, have you ever wondered: “Which webpage is actually important?” Google answered that with PageRank—treating the web as a Markov chain. Now imagine doing the same… but for transformer attention.👇 🔗 yoterel.github.io/attention_chai…

Breaking news: A large-scale, publicly accessible dataset of multi-view OLAT full-body human captures now exists. Accepted at #ICCV2025! A collaboration between MPI-INF and NVIDIA led by Timo Teufel. For Jan Kautz and me, this is our second joint work. vcai.mpi-inf.mpg.de/projects/Human…

Always only in front? Positioning cameras on head-mounted devices is crucial for ego-centric human pose estimation. Check our new #ICCV2025 work—and consider rear cameras next time when dealing with the most challenging scenarios! 4dqv.mpi-inf.mpg.de/EgoRear/ arxiv.org/pdf/2503.11652