Dr. Dimitri(o)s Mallis

Computer Vision Researcher @ SnT • PhD 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 computer vision its appliations 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 📸 !!

Research

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 as well as leveraging multimodal large language models (MLLMs) for AI-assisted design.

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.

News

Dec 03, 2024	Paper announcement 📢📢 !!! Our work entitled DAVINCI: A Single-Stage Architecture for Constrained CAD Sketch Inference was presented as an oral 🎉🎉 at the British Machine Vision Conference (BMVC) 2024! For more details check out the project page.
Dec 01, 2024	Our recent work PICASSO: A Feed-Forward Framework for Parametric Inference of CAD Sketches via Rendering Self-Supervision has been accepted for publication at WACV 2025!
Oct 03, 2024	New Paper!!! Our work on TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds will be presented on ECCV 2024.

Selected Publications [View All]

DAVINCI: A Single-Stage Architecture for Constrained CAD Sketch Inference

Ahmet Serdar Karadeniz, Dimitrios Mallis, Nesryne Mejri, Kseniya Cherenkova, Anis Kacem, and Djamila Aouada

British Machine Vision Conference (BMVC), 2024

Abs arXiv Bib URL Code

This work presents DAVINCI, a unified architecture for single-stage Computer-Aided Design (CAD) sketch parameterization and constraint inference directly from raster sketch images. By jointly learning both outputs, DAVINCI minimizes error accumulation and enhances the performance of constrained CAD sketch inference. Notably, DAVINCI achieves state-of-the-art results on the large-scale SketchGraphs dataset, demonstrating effectiveness on both precise and hand-drawn raster CAD sketches. To reduce DAVINCI’s reliance on large-scale annotated datasets, we explore the efficacy of CAD sketch augmentations. We introduce Constraint-Preserving Transformations (CPTs), i.e. random permutations of the parametric primitives of a CAD sketch that preserve its constraints. This data augmentation strategy allows DAVINCI to achieve reasonable performance when trained with only 0.1% of the SketchGraphs dataset. Furthermore, this work contributes a new version of SketchGraphs, augmented with CPTs. The newly introduced CPTSketchGraphs dataset includes 80 million CPT-augmented sketches, thus providing a rich resource for future research in the CAD sketch domain.
@article{Karadeniz2024PICASSOAF, title = {DAVINCI: A Single-Stage Architecture for Constrained CAD Sketch Inference}, author = {Karadeniz, Ahmet Serdar and Mallis, Dimitrios and Mejri, Nesryne and Cherenkova, Kseniya and Kacem, Anis and Aouada, Djamila}, journal = {British Machine Vision Conference (BMVC)}, year = {2024}, }
TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds

Elona Dupont, Kseniya Cherenkova, Dimitrios Mallis, Gleb Gusev, Anis Kacem, and Djamila Aouada

European Conference on Computer Vision (ECCV), 2024

Abs arXiv Bib URL

3D reverse engineering, in which a CAD model is inferred given a 3D scan of a physical object, is a research direction that offers many promising practical applications. This paper proposes TransCAD, an end-to-end transformer-based architecture that predicts the CAD sequence from a point cloud. TransCAD leverages the structure of CAD sequences by using a hierarchical learning strategy. A loop refiner is also introduced to regress sketch primitive parameters. Rigorous experimentation on the DeepCAD and Fusion360 datasets show that TransCAD achieves state-of-the-art results. The result analysis is supported with a proposed metric for CAD sequence, the mean Average Precision of CAD Sequence, that addresses the limitations of existing metrics.
@article{dupont2024transcad, title = {TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds}, author = {Dupont, Elona and Cherenkova, Kseniya and Mallis, Dimitrios and Gusev, Gleb and Kacem, Anis and Aouada, Djamila}, journal = {European Conference on Computer Vision (ECCV)}, year = {2024}, }
From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery

Dimitrios Mallis, Enrique Sanchez, Matt Bell, and Georgios Tzimiropoulos

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023

Abs arXiv Bib URL Code

This paper proposes a novel paradigm for the unsupervised learning of object landmark detectors. Contrary to existing methods that build on auxiliary tasks such as image generation or equivariance, we propose a self-training approach where, departing from generic keypoints, a landmark detector and descriptor is trained to improve itself, tuning the keypoints into distinctive landmarks. To this end, we propose an iterative algorithm that alternates between producing new pseudo-labels through feature clustering and learning distinctive features for each pseudo-class through contrastive learning. With a shared backbone for the landmark detector and descriptor, the keypoint locations progressively converge to stable landmarks, filtering those less stable. Compared to previous works, our approach can learn points that are more flexible in terms of capturing large viewpoint changes. We validate our method on a variety of difficult datasets, including LS3D, BBCPose, Human3.6M and PennAction, achieving new state of the art results.
@article{Mallis2023landm, author = {Mallis, Dimitrios and Sanchez, Enrique and Bell, Matt and Tzimiropoulos, Georgios}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, title = {From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery}, year = {2023}, }
Unsupervised Learning of Object Landmarks via Self-Training Correspondence

Dimitrios Mallis, Enrique Sanchez, Matt Bell, and Georgios Tzimiropoulos

Neural Information Processing Systems, 2020

Abs Bib URL PDF Supp Code

This paper addresses the problem of unsupervised discovery of object landmarks. We take a different path compared to existing works, based on 2 novel perspectives: (1) Self-training: starting from generic keypoints, we propose a self-training approach where the goal is to learn a detector that improves itself, becoming more and more tuned to object landmarks. (2) Correspondence: we identify correspondence as a key objective for unsupervised landmark discovery and propose an optimization scheme which alternates between recovering object landmark correspondence across different images via clustering and learning an object landmark descriptor without labels. Compared to previous works, our approach can learn landmarks that are more flexible in terms of capturing large changes in viewpoint. We show the favourable properties of our method on a variety of difficult datasets including LS3D, BBCPose and Human3.6M.
@article{unsupervLandm2020, title = {Unsupervised Learning of Object Landmarks via Self-Training Correspondence}, author = {Mallis, Dimitrios and Sanchez, Enrique and Bell, Matt and Tzimiropoulos, Georgios}, journal = {Neural Information Processing Systems}, year = {2020}, }

Research

News

Selected Publications [View All]

Open Source Projects