Simone Foti


Postdoctoral Researcher at Imperial College London, PhD at University College London, and internship experience at Disney Research Studios and Adobe Research. My research interest lies at the intersection of geometric deep learning, computer graphics, and computer vision. My main goal is to improve 3D generative models to democratise the creation of 3D assets for applications in AR/VR, the metaverse, the movie and game production, and in plastic surgery. Through my research I strive to understand how to solve problems in non-Euclidean domains such as graphs and meshes and I am currently working on multiple projects ranging from shape and texture generation, latent disentanglement, mesh sampling, and 3D reconstruction. 

HIGHLIGHT Publications

3D Generative Model Latent Disentanglement via Local Eigenprojection

Simone Foti, Bongjin Koo, Danail Stoyanov, Matthew J. Clarkson.

Computer Graphics Forum 2023

[paper] [arxiv] [code] [supplementary] [supplementary video]

Latent Disentanglement in Mesh Variational Autoencoders Improves the Diagnosis of Craniofacial Syndromes and Aids Surgical Planning

Simone Foti, Alexander J. Rickart, Bongjin Koo, Eimear O’Sullivan, Lara S. van de Lande, Athanasios Papaioannou, Roman Khonsari, Danail Stoyanov, N. u. Owase Jeelani, Silvia Schievano, David J. Dunaway, Matthew J. Clarkson.

Coming soon (under review)... 

[arxiv][visual abstract]

3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Faces

Simone Foti, Bongjin Koo, Danail Stoyanov, Matthew J. Clarkson.

Oral presentation at CVPR 2022

[paper] [arxiv] [code] [video] [poster] [supplementary]

Intraoperative Liver Surface Completion with Graph Convolutional VAE

Simone Foti, Bongjin Koo, Thomas Dowrick, João Ramalhinho, Moustafa Allam, Brian Davidson, Danail Stoyanov, Matthew J. Clarkson.

GRAIL-MICCAI 2020

[paper] [arxiv]

OTHER Publications

SARAMIS: Simulation Assets for Robotic Assisted and Minimally Invasive Surgery

Nina Montana-Brown, Shaheer U. Saeed, Ahmed Abdulaal, Thomas Dowrick, Yakup Kilic, Sophie Wilkinson, Meghavi Mashar, Chloe He, Alkisti Stavropoulou, Emma L Thomson, Zachary Baum, Simone Foti, Brian Davidson, Yipeng Hu, Matthew John Clarkson 

Poster at NeurIPS 2023 - Track Datasets and Benchmarks 

[paper][code and data]

Real-Time Vessel Segmentation and Reconstruction for Virtual Fixtures for an Active Handheld Microneurosurgical Instrument

Aravind Venugopal, Sara Moccia, Simone Foti, Arpita Routray, Robert A. MacLachlan, Alessandro Perin, Leonardo S. Mattos, Alexander K. Yu, Jody Leonardo, Elena De Momi, Cameron N. Riviere

IJCARS 2022

[paper]

Design and Integration of Electrical Bio-Impedance Sensing in Surgical Robotic Tools for Tissue Identification and Display

Zhuoqi Cheng, Diego Dall'Alba, Simone Foti, Andrea Mariani, Thibaud Jean Eudes Chupin, Darwin Gordon Caldwell, Giancarlo Ferrigno, Elena De Momi, Leonardo S Mattos, Paolo Fiorini.

Frontiers in Robotics and AI 2019

[paper]

Toward Improving Safety in Neurosurgery with an Active Handheld Instrument

Sara Moccia, Simone Foti, Arpita Routray, Francesca Prudente, Alessandro Perin, Raymond F. Sekula, Leonardo S. Mattos, Jeffrey R. Balzer, Wendy Fellows-Mayle, Elena De Momi and Cameron N. Rivere.

Annals of Biomedical Engineering 2018

[paper]

Advanced User Interface for Augmented Information Display on Endoscopic Surgical Images

Simone Foti, Andrea Mariani, Thibaud Chupin, Diego Dall’Alba, Zhuoqi Cheng, Leonardo Mattos, Darwin Caldwell, Paolo Fiorini, Elena De Momi, Giancarlo Ferrigno

CRAS 2018

[paper]

FCNN-Based Segmentation of Kidney Vessels - Towards Constraints Definition for Safe Robot-Assisted Nephrectomy

Sara Moccia, Simone Foti, Silvia Maddalena Rossi, Ilaria Rota, Matteo Scotti, Simone Toffoli, Leonardo Mattos, Elena De Momi and Emanuele Frontoni.

CRAS 2018

[paper]

PATENTS

Face reconstruction using a mesh convolutional network

Derek Bradley, Prashanth Chandran, Simone Foti, Paulo Fabiano Urnau Gotardo, Gaspard Zoss 

U.S. Patent Application No. 17/697,774  [patent]

INVITED TALKS

Latent Disentanglement for the Generation of 3D Digital Humans and Plastic Surgery Applications.

RE WORK | Deep Learning London AI Summit 2022