Simone Foti
@simo_foti
Followers
147
Following
91
Media
8
Statuses
32
Postdoc at Imperial College London. Research in latent disentanglement, geometric deep learning, computer vision, and computer graphics.
London, England
Joined February 2022
🚨 It's confirmed, "UV-free Texture Generation with Denoising and Geodesic Heat Diffusions" just landed at #NeurIPS2024! No more UV map struggles—just point cloud textures & heat diffusion magic. 🔥 Curious? Keep reading. Oh, and definitely turn up the audio 🎧👇
10
50
320
Months of planning, and it's over in a flash! Seeing #LOGML come to life with such a fantastic group was worth every bit of effort. The collaborative spirit during the projects was exactly what we hoped for. Immense gratitude to all who came and made the week a huge success. 👏.
And that's a wrap on the LOGML 2025 Summer School! 🚀. We’ve been quiet on here, but that’s because we were busy with 100 brilliant minds diving deep into geometry, ML, and social activities. 😉
0
2
11
Blazing-fast image creation – using just your voice. Try Grok Imagine.
277
541
3K
LOGML 2025 is shaping up to be incredible! 🔥 .If you're into geometry & ML, this is your chance to dive deep, meet top researchers, and work on projects that matter—all in London 🇬🇧 with an amazing community. Trust me, it's as fun as it is inspiring. Apply now! ⏳👇.
🌟Applications open- LOGML 2025🌟. 👥Mentor-led projects, expert talks, tutorials, socials, and a networking night.✍️Application form: 📅Apply by 6th April 2025 .✉️Questions? logml.committee@gmail.com . #MachineLearning #SummerSchool #LOGML #Geometry.
1
2
7
💡Excited by geometry & ML like our organizing committee?💡. Mentor at LOGML 2025 and help shape projects that can become top publications. It’s academic, social, and seriously fun—Plus, it’s in London 🇬🇧 (July 7-11) and we’ve got you covered. Apply now 👇👇👇.
⭐️Mentor applications open⭐️. We're excited to announce that LOGML summer school will return in London: July 7-11 2025. We are seeking mentors to lead group projects at the intersection of geometry and machine learning. Find out more and apply: .
0
1
9
Quick hits:.✨Avoid seams, distortions, non-uniform resolution or wasted UV space!.✨Textures are represented and generated directly onto the objects' surface by UV3-TeD. ✨UV3-TeD is a denoising diffusion model (DDPM) based on our attention-enhanced heat diffusion.
1
1
8
🎙️ Did you turn up the volume of the video??? Yes, it's exactly what you’re thinking—an AI-generated podcast of the paper!. Want the full podcast? Want to play with the code? Head to our project website for all that (and model weights). 🖥️🎶👇.
1
0
8
RT @tolga_birdal: Beyond 3D representations, we must rethink appearance too—textures specifically. UV-maps, the de-facto standard, have inh….
0
57
0
👥Team: @simo_foti, Alex Rickart, @BongjinKoo, Eimear O’Sullivan, Lara van de Lande, @apapaion, @RH_Khonsari, @DanStoyanov, @DrOJeelani, Silvia Schievano, David Dunaway, and @MattClarksonUCL. @GoshCranioRes & @ucl_compass.
0
1
3
🚀 This paper just scratches the surface of what SD-VAE can do for craniofacial applications. There’s much more to come—stay tuned! 🙂.
1
0
1
The paper is published in Computer Methods and Programs in Biomedicine and titled "Latent Disentanglement in Mesh Variational Autoencoders Improves the Diagnosis of Craniofacial Syndromes and Aids Surgical Planning." . Full article here:
1
0
0
By leveraging the disentangled representation of SD-VAE (which we introduced in #CVPR2022), we identified key morphological features that contribute to each syndromic phenotype. This allowed us to diagnose these conditions and even predict the outcomes of craniofacial surgeries!
1
0
0
🚨 After a mere 408 days in review, my last PhD paper is finally out! . Turns out, machine learning for computer vision and graphics isn’t just for flashy visuals. We found it can actually help babies with rare craniofacial deformities. Who would’ve guessed? 🤔👶
1
1
8
👥Team: @simo_foti, @BongjinKoo, @DanStoyanov, @MattClarksonUCL. If you are interested, don't forget to check out the team's previous CVPR 2022 paper on "3D Shape VAE Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Faces" (!.
0
2
2
"3D Generative Model Latent Disentanglement via Local Eigenprojection" introduces a new loss function grounded in spectral geometry and applicable to different neural-network-based generative models of 3D head and body meshes. 🤖Code:
1
0
0
🚀New paper!🚀. Are you tired of generative models that limit your control over the creation of local shape attributes in 3D digital humans? . 🔍Check out our latest paper in Computer Graphics Forum 2023
2
1
3
RT @teamrework: A great presentation from Simon Foti, PhD in Geometric Deep Learning at UCL! Simon is giving providing an overview of recen….
0
2
0
Check out our #CVPR2022 paper on 3D VAE Latent Disentanglement via Mini-Batch Feature Swapping. Find out how to properly decouple the generation of identity features of 3D faces and bodies at
2
2
5