Martin N. Everaert Martin Nicolas Everaert

About Me

Fourth-year PhD candidate in the Image and Visual Representation Lab at EPFL. Currently looking for a PhD internship (Resume).

Research: Computer Vision and Generative AI, focus on Text-to-Image Diffusion Models

I am currently a fourth-year PhD candidate in the Image and Visual Representation Lab (IVRL) at EPFL. I am grateful to be supervised by my PhD advisor Prof. Dr. Sabine Süsstrunk and my PhD co-advisor Dr. Radhakrishna Achanta.

I am interested in Computational Aesthetics, overlapping with Computation and Language, Computer Vision, Deep Learning, Generative Models, etc. My research specifically focuses on Text-to-Image Diffusion Models.

Prior to pursuing my PhD, I completed a Master's in Computer Science at EPFL in 2021. I also hold a Diplôme d'Ingénieur (engineering BS/MS degree) from the Supélec curriculum at CentraleSupélec, graduating concurrently in 2021, and a BS degree in Fundamental Physics from Université Paris-Sud in 2018. Before that, I attended Lycée Saint Louis, where I pursued French preparatory classes (CPGE), with a focus on Math, Physics, Engineering and Computer Science (MPSI/MP*). Throughout my studies, I also interned at Thales Group (Master's thesis project, 2021), CEA (Engineering internship, 2019), and TCL Corporation (1-month Work/Labor internship in Chengdu, China, 2018).

Publications

Covariance Mismatch in Diffusion Models [Preprint  2024]

M. N. Everaert, S. Süsstrunk, and R. Achanta. “Covariance Mismatch in Diffusion Models”, Infoscience preprint 20.500.14299/242173, 2024.

Exploiting the Signal-Leak Bias in Diffusion Models [WACV 2024]

M. N. Everaert, A. Fitsios, M. Bocchio, S. Arpa, S. Süsstrunk, and R. Achanta. “Exploiting the Signal-Leak Bias in Diffusion Models”, WACV 2024. (accepted in round 1)

VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text [BMVC 2023]

M. N. Everaert, M. Bocchio, S. Arpa, S. Süsstrunk, and R. Achanta. “VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text”, BMVC 2023.

Diffusion in Style [ICCV 2023 + Patent PCT filed]

M. N. Everaert, M. Bocchio, S. Arpa, S. Süsstrunk, and R. Achanta. “Diffusion in Style”, ICCV 2023 + Patent PCT filed.

Estimating Image Depth in the Comics Domain [WACV 2022]

D. Bhattacharjee, M. N. Everaert, M. Salzmann, and S. Süsstrunk. “Estimating Image Depth in the Comics Domain”, WACV 2022.

Aesthetics-Oriented Video Generation and Editing

M. N. Everaert. “Aesthetics-Oriented Video Generation and Editing”, EDIC research proposal, 2022.

Scene relighting with illumination estimation in the latent space on an encoder-decoder scheme

A. P. Dherse*, M. N. Everaert*, and J. J. Gwizdała*. “Scene relighting with illumination estimation in the latent space on an encoder-decoder scheme”, arXiv preprint arXiv:2006.02333, 2020.

* equal contribution

Academic activities

Conferences services

Check out ICCP 2024 website

Reviewer for NeurIPS 2024
(6 reviews)

Reviewer + emergency reviewer for ECCV 2024
(2 reviews, 1 emergency review)

Emergency reviewer for BMVC 2023
(9 emergency reviews)

Reviewer for ICCV 2023
(1 review, 1 emergency review)

You can find my name on the BMVC 2023 emergency reviewers list and on the ICCV 2023 reviewers list.

Talks and presentations

AI Tinkerers Lausanne Inaugural Meetup, June 2024: news, event page, LinkedIn post

Public presentation of candidacy exam, 2022: event page, writeup

Controlling Style in Diffusion Models through the Noise (ICCP 2024): video
(1-min research video)

Exploiting the Signal-Leak Bias in Diffusion Models (WACV 2024): video
(📝 Paper video)

VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text (BMVC 2023): video
(📝 Paper video)

Diffusion in Style (ICCV 2023): video
(📝 Paper video)

Controlling Style in Diffusion Models through the Noise, at ICCP 2024: poster
(Research poster, ✨ ICCP2024 Spotlight poster ✨)

Controlling Style in Diffusion Models through Noise, presented at ICVSS 2024: poster
(Research poster)

Image Generation with Diffusion Models, presented at EDIC Open House 2024: poster
(Research poster)

Exploiting the Signal-Leak Bias in Diffusion Models, presented virtually at WACV 2024: poster
(📝 Paper poster)

VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text, presented at BMVC 2023: poster
(📝 Paper poster)

Diffusion in Style, presented at ICCV 2023: poster
(📝 Paper poster)

Awards

Teaching assistant Award from EPFL School of Computer and Communication Sciences (IC) for teaching excellence (2023)

EDIC PhD fellowship (2021)

Teaching and student supervisions

Teaching assistant (TA)

Teaching assistant for CS-413: Computational Photography, taught by Prof. Sabine Süsstrunk: Spring 2022, Spring 2023 (TA Award!), Spring 2024

Teaching assistant for CS-328: Numerical Methods for Visual Computing and Machine Learning, taught by Prof. Wenzel Jakob: Fall 2021, Fall 2023

Supervision of MS and BS students

  • 1 MS student. “Using Large Language Models (LLMs) as Diffusion Models for Image Generation”, Master research project, Spring 2024, project description, co-supervised with Dongqing Wang.

  • 1 BS student. “Exploring the Benefits of 2D Gaussian Splatting in Image Representation and Compression”, Bachelor research project, Spring 2024, project description, project report.

  • 1 BS student. “Feed-Forward Guidance for Text-to-Image Diffusion Models”, Bachelor research project, Fall 2023, project description.

  • 1 MS student. “Generating stories from keywords”, Master semester project, Spring 2023, project description.

  • 1 BS student. “Coreference resolution for story visualization”, Bachelor semester project, Spring 2023, project description.

  • 1 MS student. “Generate images from texts”, Master semester project, Fall 2022, project description.

  • 1 BS student. “Is this video an ad?”, Bachelor semester project, Fall 2022, project description.

  • 1 team of 3 MS students + 1 team of 2 MS & 1 PhD students. “360°-photography: Stitching dual fish-eye images”, Spring 2024, project description.

  • 1 team of 3 MS students. “Computational photography with smartphone lenses”, Spring 2024, project description.

  • 1 team of 3 MS students. “Automatic and Personalized Tunnel Book Generation from Photographs”, Spring 2024, project description.

  • 1 team of 1 MS student. “2D Gaussian Splatting for Image Representation and Compression & Text to 2D Gaussian Splatting”, Spring 2024, project description.

  • 1 team of 3 MS students. “Aesthetics of sets of images”, Spring 2023, project description.

  • 1 team of 3 MS students + 1 team of 2 MS students. “TimeWarp: How would this scene look in 100 years?”, Spring 2023, project description.

  • 2 teams of 3 MS students. “Text to Photomosaic”, Spring 2023, project description.

  • 1 team of 3 MS students. “From RGB to NIR with Style Transfer”, Spring 2023, project description.

  • 1 team of 3 MS students. “Improving an open-source microscope by adding multispectral imagery”, Spring 2022, project description.

  • 2 teams of 3 MS students. “Low-level image transformations for image aesthetics”, Spring 2022, project description.

  • 1 team of 3 MS students. "Predicting if two frames are part of the same video", ML4Science project, Fall 2022, project report, project code.

Martin Nicolas Everaert
Designed with w3.css