p

🚀 Excited to unveil our latest #ECCV2024 paper: "SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes”where we show how to extract keypoints from non-rigid point clouds without supervision 📚✨ 🧵1/4

Multimodal Learning & Applications workshop @CVPR2024 has just started and the room is fully packed with 50+ attendees! Check out the full program at mula-workshop.github.io. Organised together with @Michael74726307 @paolorotaphd @pmorerio @vmurino & Bodo

Here we go. The 7th edition of MULA starts now!! #cvpr2024

@massi_manc is doing his keynote at Summit 320 now!! #cvpr2024

PAVIS team will be at Seattle for @CVPR 2024. Meet @pmorerio, @gianscarpe_phd, @SFiorini94, @alessiodelbue at Equivision (Tue 18/Summit 321), C3DV (Tue 18/Summit 327) and Embodied AI workshops (Tue 18/Summit 428); presenting DiffAssemble poster on Fri 21. youtu.be/jTWcb9izvLo?si…

@SciFi cool stuff 😉

Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation. arxiv.org/abs/2404.10574

🚀 Great News! 🚀 Our new paper "Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation", which extends our previous CVPR23, is available online: arxiv.org/abs/2404.10574. @TalonDavide @sebattiato @alessiodelbue @pmorerio

Today @mgpadalkar is presenting his start-up project NirvanaVisor, using mixed reality and computer vision to support people with vision-related problems. #startup #ai #mixedreality #computervision @IITalk @alessiodelbue

Check our paper "HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior" Authors: @SvitovDavid, @pmorerio, @LourdesAgapito, @alessiodelbue Project page: david-svitov.github.io/HAHA_project_p… Arxiv paper here: arxiv.org/abs/2404.01053 Video: youtu.be/vBzdAOKi1w0?si… 4/4

HAHA is our new method for generating animatable human avatars from monocular video by combining mesh and 3D Gaussian Splatting (3DGS)! 🕺💃 HAHA optimizes the number of Gaussians in an avatar and reduces storage costs and the number of artefacts. Check our thread 🧵... 1/4

@paolorotaphd @alessiodelbue @vmurino @rvolpis @I4c0p0 🤪 science

Back in Genova after a few years. Science ✔️ Company ✔️ Food ✔️ Thanks for inviting me, @alessiodelbue @vmurino @pmorerio @rvolpis @I4c0p0 & andre.

Our new ICRA 2024 paper is out, solving pose estimation using a NeRF model in real-time!

📄 Read on arXiv: arxiv.org/abs/2402.19302 or check our code at github.com/IIT-PAVIS/Diff… and webpage at iit-pavis.github.io/DiffAssemble/ 🙏 Congrats to the @IITalk team for their dedication and hard work! @gianscarpe_phd, @FGiuliari93, @SFiorini94, @pmorerio, @alessiodelbue

🧩 Excited to unveil our latest #CVPR2024 paper! 🚀 DiffAssemble: a groundbreaking diffusion model solving puzzle reassembly challenges in both 2D and 3D spaces. Bye-bye noise, hello perfect reconstruction! 🎉 #GenAI #DiffusionModels 🔍 Dive into the details with our thread!👇

. #IA e #lavoroparlamentare: nel report sull’indagine conoscitiva svolta dal Comitato di vigilanza sull’attività di documentazione della Camera dei deputati anche il contributo di Alessio Del Bue, Responsabile del laboratorio IIT @PAVIS_IIT. opentalk.iit.it/chiamata-per-l…

📢 Website alert for #MULA2024 enthusiasts! 🚀 The 7th Multimodal Learning and Applications Workshop site is now fresh & updated. 🔗mula-workshop.github.io #CVPR2024

@paolorotaphd looking forward to the workshop!

...and we are #hiring again! PAVIS @IITalk is searching for two postdocs on multi-modal learning and spatial audio processing to join us on a new European Project on Mixed Reality. More info here, deadline 22 December: iit.taleo.net/careersection/…

Today I‘m presenting our work Semantic Disagreement for Embodied Active Perception at Out-of-distribution generalization in computer-vision workshop at #iccv2023. Reach out if you are interested!

Today we are at Synapse symposium organised by @bendingspoons in Milan with PAVIS (pavis.iit.it) team: @FGiuliari93, @gianscarpellini @sanketsans97, @vmurino. Amazing line-up of speakers: synapsesymposium.ai #SynapseAISymposium