GeoGen3DHuman

Our paper “Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads” has been accepted to International Journal of Computer Vision (IJCV, top computer vision journal) Special Issue on Audio-Visual Generation!  @miccunifi @CNRS_HdF

We are pleased to announce an international seminar organized as part of the CNRS International Research Project (IRP) Geometric Deep Learning and Generative Models for 3D Human. Participation in this seminar is open to all interested participants. @miccunifi @CNRS_HdF

🎙️ Thomas Besnier gave a talk during his visit to MICC, as part of the IRP GeoGen3DHuman project — great insights and discussions! #Research #AI #MICC #GeoGen project — great insights and discussions! @miccunifi @CNRS_HdF

Welcome to Muhammad Zain Amin a new PhD student started a Joint PhD thesis since October 1st. This thesis is funded by the University of Florence and the Region Hauts-de-France. @miccunifi @stefano_berrett @hautsdefrance @CNRSinformatics @CNRS_HdF

ScanTalk has been presented during the International Computer Vision Summer School 2024 by Federico Nocentini @stefano_berrett @cnrs_hdf @CNRSinformatics

ScanTalk has been presented during the national conference CORESA 2024 (COmpression et REprésentation des Signaux Audiovisuels) by Thomas Besnier. @ThomasBesnier11 @CNRS_HdF @stefano_berrett @miccunifi

Professors Mohamed Daoudi, Alberto Del Bimbo and Stefano Berretti were co-organizers of the first International Spring School, Multimodal Foundation Models and Generative AI 2024, Rabat (Morocco), April 29 - May 3, 2024. @miccunifi @CNRS_HdF @stefano_berrett @CNRSinformatics

We are presenting ScanTalk @eccvconf The paper at: arxiv.org/pdf/2403.10942 The code on GitHub: github.com/miccunifi/Scan… Collaboration between #CRIStAL and @miccunifi under the CNRS IRP project geogen3dhuman.univ-lille.fr #GenAI #face #audio #3D @CNRSinformatics @CNRS_HdF

Excited to share that our paper « ScanTalk: 3D Talking Heads from Unregistered Scans » is accepted at #ECCV2024! ScanTalk is a novel Speech-driven 3D talking heads generation framework capable of animating 3D faces in arbitrary topologies arxiv.org/abs/2403.10942

Voici Matthew Walker. Il est le meilleur scientifique du sommeil du 21e siècle. Son message ? Plus votre sommeil est court, plus votre vie est courte. Voici son protocole appuyé par des preuves pour obtenir un sommeil de haute qualité chaque nuit :

Dad is an engineer... Ta taaaaaaaa 😂

I get asked a lot: why stay in academia, all the excitement in AI is happening in industry with massive compute. And I am seeing some profs leaving academia, but also seeing lots of researchers in industry looking to go back to academia, especially those who don’t work on LLMs. I have spent some time and actively working with industry, and it has been a great experience, but for me the answer is simple: 1. Students: Nothing can replace working with really smart & amazing students. 2. Academic freedom: In general, industry will one way or another dictate what you should work on. Today it is LLMs, tomorrow it is something else. The good old days of "here is a cool idea, let me investigate and publish" are pretty much over. But as an academic, I can work on whatever I want: I can start working on "black holes" tomorrow if I choose to. 3. And my favourite one: No reorgs -- big tech really loves reorgs that happen every few months. Finally, as an academic, I can always take some time off, work in industry or start-up, and come back if I want to. Going into industry is usually a one-way street: It is far easier to go to industry from academia and much harder the other way around.

#ICIAP2023 main conference will end on Thursday September 14th! All the conference activities are taking place at @uniud's Polo Economico-Giuridico (📍 goo.gl/maps/jagAVDCvK…) from 9am to 4.30pm. ➡️ sites.google.com/view/iciap-202… Follow the thread for more information ⬇️

The proceedings of #ICIAP2023 main conference are online! 📄📄📄 ➡️ link.springer.com/book/10.1007/9… ➡️ link.springer.com/book/10.1007/9…

The workshop on Generation of Human Face and Body Behaviour is organized by @DaoudiMed64, @stefano_berrett, and is running from 2pm to 5.30pm. ➡️ sites.google.com/view/ghb2023

Today is the first day of the Symposium on 3D Object Retrieval 2023 (3DOR’23)

3 greats talks given at #3DOR 2023 by ： - Maks Ovsjanikov, Efficient general-purpose feature learning for 3D shape comparison. - Stefanie Wuhrer, Learning representations of 4D human motion. - Angela Dai, Learning from Synthetic 3D Priors for Real-World 3D Perception.

The 16th Symposium on 3D Object Retrieval 2023 (3DOR'23) will be held at Lille on August 31 and September 1. The detailed conference program of 3DOR'23 is available at sites.google.com/view/3dor2023/…