Dr. Dimitri(o)s Mallis

Computer Vision Researcher @ SnTPhD from the University of Nottingham.


Welcome!! 👋 I am a Postdoctoral Researcher at the Interdisciplinary Centre for Security, Reliability and Trust (SnT) of the University of Luxembourg, focusing on 3D Computer Vision and it’s applications for Computer-Aided Design (CAD).

I received my PhD in Computer Vision at the University of Nottingham under the supervision of Dr. Yorgos Tzimiropoulos. I was also a Research Intern at Samsung AI Cambridge (SAIC) and later a Senior Machine Learning Engineer for Taboola and Deeplab.

In this website you can find more info about me, check publications and recent news. You can also browse through my photography here 📸 !!


Currently my focus in on 3D vision and it’s application towards accelerating parametric Computer-Aided Design (CAD). I am particularly interested in automated reverse engineering of 2D/3D CAD models, effective recovery of construction history and capturing of design intent.

During my PhD, I concentrated on learning with minimal manual supervision through self-supervised and semi-supervised learning, specifically for the tasks of landmark detection and human pose estimation. Later, I also looked into deep learning based recommender systems and the problem of click-through-rate (CTR) prediction.


Dec 17, 2023 New Paper!!! Our work on Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction will be presented on WACV 2024.
Oct 01, 2023 Great news to share: Our paper on Interpretable Visual Question Answering Via Reasoning Supervision will be presented on ICIP 2023 as a lecture 🎉. Great work from Maria Parelli 🎉. Thanks to all authors, Markos Diomataris and Vassilis Pitsikalis and Deeplab for a great collaboration.
Sep 10, 2023 Happy to share that our paper entitled SHARP 2023 Challenge: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines will be presented at the SHARP2023 ICCV Workshop.
Apr 01, 2023 I have now started my new position as Postdoctoral Researcher at the SnT, Interdisciplinary Centre for Security, Reliability and Trust of the University of Luxembourg.
Jan 04, 2023 Our paper From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery has been accepted for publication at IEEE Transactions on Pattern Analysis and Machine Intelligence. The paper extends our NeurIPS 2020 work on unsupervised landmark discovery both conceptually and experimentally!

Selected Publications [View All]

  1. TPAMI2023_preview.jpg
    Dimitrios Mallis, Enrique Sanchez, Matt Bell, and Georgios Tzimiropoulos
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
  2. NEURIPS2020_preview.jpg
    Dimitrios Mallis, Enrique Sanchez, Matt Bell, and Georgios Tzimiropoulos
    Neural Information Processing Systems, 2020

Open Source Projects