Eric-Tuan Le

I am currently in my final year doing a PhD in the Smart Geometry Processing Group, which is part of the School of Computer Science at University College London. Under the co-supervision of Iasonas Kokkinos and Niloy J. Mitra, my research revolves around Deep Learning, Computer Vision, and Computer Graphics. Specifically, I have been focusing on 3D representation and reconstruction.

I hold two Master's degrees: one in Applied Mathematics from CentraleSupelec, where I graduated with the highest honors and achieved the best overall grade in my class, and another in Machine Learning and Computer Vision (Master MVA) from Ecole Normale Supérieure Paris-Saclay (formerly known as ENS Cachan).

In 2020, I had the opportunity to intern remotely at Adobe Research in San Jose, where I worked on primitives' fitting for large 3D point clouds. Then, in 2022, I interned at Snap Inc. London, where my project involved 3D body mesh reconstruction from 2D images with improved 2D reprojection accuracy. Currently, I am interning at Meta AI in London until December 2023.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo
StyleMorph: Disentangled 3D-Aware Image Synthesis with a 3D Morphable StyleGAN
Eric-Tuan Le*, Edward Batrum*, Iasonas Kokkinos
ICLR, 2023
project page / paper / supplementary / bibtex / video / code

We introduce StyleMorph, a 3D-aware generative model that disentangles 3D shape, camera pose, object appearance, and background appearance for high quality image synthesis. We chain 3D morphable modelling with deferred neural rendering by performing an implicit surface rendering of “Template Object Coordinates” (TOCS).

Softmesh: Learning Probabilistic Mesh Connectivity via Image Supervision
Eric-Tuan Le, Iasonas Kokkinos, Niloy J. Mitra
3DV, 2021
paper / bibtex

We introduce Softmesh, a fully differentiable pipeline to transform a 3D point cloud into a probabilistic mesh representation that allows us to directly render 2D images.

Cascaded Primitive Fitting Networks for 3D Point Clouds
Eric-Tuan Le, Minhyuk Sung, Duygu Ceylan, Radomir Mech, Tamy Boubekeur, Niloy J. Mitra
ICCV, 2021
project page / paper / supplementary / bibtex / code

We present Cascaded Primitive Fitting Networks (CPFN) that relies on an adaptive patch sampling network to assemble detection results of global and local primitive detection networks. As a key enabler, we present a merging formulation that dynamically aggregates the primitives across global and local scales.

Going Deeper with Lean Point Networks
Eric-Tuan Le, Niloy J. Mitra, Iasonas Kokkinos
CVPR, 2020
project page / paper / supplementary / bibtex / code

We train deeper and more accurate point processing networks by introducing three modular point processing blocks that improve memory consumption and accuracy. By combining these blocks, we design wider and deeper point-based architectures.

Work Experience
June to December 2023: Research Intern at Meta AI
June to December 2022: Research Intern at Snapchat AR
June to November 2020: Research Intern at Adobe Research
Unifying DensePose and 3D Body Mesh reconstruction, ongoing application, filled by Snap Inc
Eric-Tuan Le, Antonis Kakolyris, Petros Koutras, Himmy Tam, Efstratios Skordos, Riza Alp Guler, George Papandreou,
Iasonas Kokkinos
Fitting 3d primitives to a high-resolution point cloud, US20220292765A1, filled by Adobe Inc
Eric-Tuan Le, Duygu Ceylan, Tamy Boubekeur, Radomir Mech, Niloy J. Mitra, Minhyuk Sung
Computer Vision conferences:
Reviewer for CVPR 2021, 2022, 2023
Reviewer for ICCV 2021, 2023
Reviewer for ECCV 2022
Computer Graphics conferences:
Reviewer for SIGGRAPH Asia 2022
Machine Learning conferences:
Reviewer for NeurIPS 2023
2018-2023: PhD in Computer Vision at University College London
Co-supervised by Iasonas Kokkinos and Niloy J. Mitra
2016-2017: MSc in Machine Learning and Computer Vision at Ecole Normale Supérieure de Cachan
GPA: 4.00 (range from 0 to 4) - Graduated with Highest Honors (Overall grade: 17.49/20)
2014-2017: Master in Management at ESCP Europe
Z-Score: 1.89 (range from -3 to 3) - Graduated with Highest Honors
2013-2017: MSc in Applied Mathematics at CentraleSupelec
GPA: 3.98 (range from 0 to 4) - Graduated with Highest Honors
Teaching Assistant for Machine Learning Seminar led by Prof. Marc Deisenroth and Prof. Brooks Paige (2021)
Teaching Assistant for Machine Learning for Visual Computing led by Prof. Niloy J. Mitra and Prof. Tobias Ritschel (2020-2021)
Teaching Assistant for Computer Graphics led by Prof. Tobias Ritschel (2019)
Teaching Assistant for Acquisition and Processing of 3D Geometry led by Prof. Niloy J. Mitra (2019-2020)
Teaching Assistant for Introduction to Machine Learning led by Prof. Iasonas Kokkinos (2019-2021)
Teaching Assistant for Machine Vision led by Prof. Gabriel Brostow (2018)
Teaching Assistant for Information Retrieval and Data Mining led by Prof. Emine Yilmaz (2018)
Teaching Assistant for Algorithms led by Prof. Ifat Yasin (2018)
Teaching Assistant for Requirements Engineering and Software Architecture and Software Systems Integration led by Prof. Emmanuel Letier (2018-2022)

Source code from Jon Barron's website