People

Eddy Ilg

I became a professor at Saarland University in June 2022 and lead the CVMP lab.

Previously I worked in the US at Meta Reality Labs on project LiveMaps which aims to build a complete machine perception stack for augmented reality, ranging from hardware to mapping and localization as well as 3D scene understanding up to photorealistic 3D reconstruction. This work gifted me with a very broad perspective on AI and an understanding of the challenges involved in building AI systems.

I obtained my Ph.D. from the University of Freiburg and I am very well known for my work on optical flow, which led to a paradigm shift and first established deep learning approaches in the field. Furthermore, I am known for my work in related areas on the estimation of disparities, motion, occlusion boundaries, occlusions as well as uncertainties. Please have a look at my thesis.

During high school, I wrote an operating system and won the prize for the best work in software engineering at the German young researcher’s federal contest. I am generally a very curious and creative person. During my studies, I was supported by a scholarship from the German Academic Scholarship Foundation for extraordinarily talented students with a vast horizon.

My current research interests lie in bringing AI systems to the next level and using deep learning in combination with 3D computer vision, computer graphics, and NLP. My vision is to combine research from these areas to build AI systems that are not rigid and can evolve over time.

During my PhD, I have previously had the chance to lead a small team and a strong team atmosphere is very important to me. Research is fundamentally about moving forward into the unknown and I personally find it invaluable to have many diverse perspectives on one’s work. Therefore I support working in small teams with an intensive discussion culture and a healthy team atmosphere. To my students, I serve as a mentor in aspects of their careers ranging from theory to engineering and from academia to industry.

Raza Yunus

I am a Ph.D. student since December 2022, jointly at the CVMP lab and Max Planck Institute for Informatics (MPI).

I did my Bachelor’s in Software Engineering at NUST, Pakistan, and my Master’s in Informatics at TU Munich, with a focus on Computer Vision and AI. During my thesis, I developed ManhattanSLAM, a robust SLAM system that utilizes structure in indoor scenes for accurate camera pose tracking.

My research interests lie in 3D Computer Vision and Simultaneous Localization and Mapping (SLAM) in general. Currently, I’m focusing on non-rigid 3D reconstruction, where the goal is to eventually track and reconstruct complete dynamic scenes in real-time, using a single camera.

I like to play music, read, or pop a game of chess in my free time.

Tom Fischer

Starting April 2023, I will be a Ph.D. student in the CVMP lab under the supervision of Prof. Ilg.

I did my Bachelors in Cybersecurity and my Masters in Computer Science at Saarland University.
During my later studies I focused on Computer Vision and Machine Learning, which lead to me joining the CVMP lab for my master thesis.

For my thesis, I investigated if and how it is possible to embed explicit diffusion evolutions in deep learning approaches for optical flow.
We conjectured, that using the well-understood diffusion modelling theory lets us design more explainable and stable networks to solve the optical flow problem efficiently.

When I am not staring at a computer screen, I like to cook and experiment with different recipes and cuisines. I love eating out with friends and I am always looking for restaurant recommendations!

Kaelble Jonas

I am a Ph.D. student working with the Bosch Center for Artificial Intelligence in Renningen and Prof. Ilg from the CVMP lab.

I did my Bachelor’s and Master’s in Electrical Engineering and Information Technology at Karlsruhe Institute of Technology. During my Master’s, I specialized in signal processing and  especially focused on machine learning for computer vision and perception tasks. I investigated the fusion of camera images and LIDAR pointclouds at the Forschungszentrum Informatik in Karlsruhe.

My current research focuses on the task of perceiving the environment in the context of autonomous driving. To this end, I am working on the reconstruction of dynamic scenes using multiple cameras mounted on a vehicle. In my free time, I like to play basketball and go mountain biking.

Cameron Braunstein

I have been a PhD student as a member of the RTG: RTG 2853 Neuroexplicit Models of Language, Vision, and Action since October 2023. I am cosupervised by Eddy Ilg and Mariya Toneva. My current research focuses on developing neuroexplict vision-language models. An additional goal of my research is to study how these models align with human brain activity.

I have a Bachelor’s degree in Computer Science and Mathematics from Brandeis University, and a Master’s degree in Data Science and Artificial Intelligence from Saarland University. For my Master’s thesis, I investigated techniques for integrating quantum computing into computer vision.

In my spare time, I enjoy cooking, watching movies, playing chess, and playing the piano works of Claude Debussy.

Noor Ahmed

I am a PhD student at the CVMP Lab under the supervision of Professor Eddy Ilg.

I completed my Bachelor’s in Computer Science from National University of Computer and Emerging Sciences, Pakistan. Following that, I worked as a Computer Vision Engineer at OMNO AI, a startup bringing Vision and AI systems for customer analysis to fashion retailers and stores. For my masters, I was enrolled in the Visual Computing program at Saarland University. Complementary to this, I did my master thesis at the D2—Computer Vision and Machine Learning Group at MPII—under the supervision of Dr. Bernt Schiele and advisory of Anna Kukleva. My work proposed the OrCo method, which improved generalisation for Few-Shot Class Incremental Learning (FSCIL) via a novel contrastive loss.

My research primarily lies within the realm of continual learning. I plan to diversify my research portfolio by extending continual learning to settings including and beyond 2D data.

My passion for research only just surpasses that for cooking. My best ideas tend to arrive at nightfall. I would also like to produce my own music album at some point in life.

Sohaib Zahid

I am doing Master’s in Computer Science at Saarland University since November 2021. My primary interests have been Computer Graphics, Computer Vision and Deep Learning.

Currently, I am working on my Master’s thesis on a collaborative project between CVMP and MPI, under joint supervision from Prof. Eddy Ilg and Vladislav Golyanik. The focus of the thesis is on extending the capabilities of Neural Rendering approaches for Event Cameras.

Before starting my Master’s, I worked as a Research Assistant at National Center of Artificial Intelligence in Pakistan, under the supervision of Prof. Faisal Shafait. My work revolved around document processing and information extraction using deep learning. I did my Bachelor’s in Software Engineering (2015-2019) from NUST, Pakistan.

In my free time I like to cook, watch movies, do a bit of sim-racing and occasionally go for swimming.

Pranay Raj Kamuni

I am currently pursuing a Master’s degree in Visual Computing at Saarland University, where I am passionate about exploring the intersections of computer vision, computer graphics, and machine learning.

I obtained my Bachelor’s degree in Electrical Engineering from the Indian Institute of Technology (IIT) Bhubaneswar in 2019, where I focused on signal systems and image processing, as well as machine learning. This foundation has been instrumental in shaping my current research.

My master’s thesis focuses on Relightable Scene Rendering, which involves using ideas from Computer Graphics and Computer Vision to create and manipulate digital visual content for various applications. Under the guidance of Prof. Eddy Ilg (CVMP) and Dr. Marc Habermann (MPII), I am exploring the potential of these techniques to generate photorealistic 3D models of real-world objects that can be rendered with dynamic lighting and camera positions.

In my free time, I enjoy playing sports, watching movies, and exploring the outdoors.

Navdeeppal Singh

I am currently a Master’s student studying Computer Science at the Saarland University, where I also obtained my Bachelor’s degree in Computer Science in 2021. I am interested in computer vision, neural search, as well as robust and interpretable neural networks.

For my Bachelor’s thesis, I worked on the robustness evaluation of inherently interpretable neural network models.

At the CVMP Lab, I will be writing my Master’s thesis, for which I will be working on fine-grained classification using generative neural mesh models, under the supervision of Prof. Eddy Ilg and Dr. Adam Kortylewski.

Ahsan Jalil

I am currently pursuing a Master’s in Visual Computing at Universität des Saarlandes since April 2022.

I completed my Bachelor’s in Electrical Engineering from the National University of Computer & Emerging Sciences (Lahore, Pakistan) in 2020, after which I worked for almost 2 years as an Algorithms Engineer for the industry. My technical interests include Image Processing and Computer Vision.

Currently, I am working on my Master’s thesis under the supervision of Prof. Eddy Ilg at the CVMP lab in the area of Neural Inverse Rendering and SLAM. I am also working part-time as a Junior Researcher at Deutsche Forschungszentrum für Künstliche Intelligenz. I enjoy traveling, playing video games, and photography to unwind whenever I can.

Xiaojie Zhang

I am a Master’s student in Visual Computing at Saarland University. My interests lie in the areas of computer vision and deep learning. During my Master’s studies, I have discovered a passion for 3D Computer Vision, which I am pursuing at CVMP.

I completed my Bachelor’s degree in Computer Science at Zhejiang International Studies University, China, from 2018 to 2022. At the CVMP lab, I am currently responsible for implementing exercises for the 3D Computer Vision lecture.

Outside the study sphere, I am a lover of powerlifting and hiking in forests, also I am a big fan of hip-hop music.

Hevra Petekkaya

I am a master’s student in the Data Science and Artificial Intelligence program at Saarland University and joined the CVMP lab in the winter semester of 2023. I completed my bachelor’s degree in Computer Engineering at Middle East Technical University North Cyprus Campus. My bachelor’s thesis, which was a team work, focused on building a navigation assistance model for visually impaired people that was inspired by Dist-YOLO paper. 

My interest lies in researching different kinds of mathematical approaches to understand and formulate intelligence. I believe that working on vision is a reasonable path to understanding it. Currently, I am supporting a project related to diffusion and neuroexplicit-models.

In my free time, I like watching movies and reading various topics. I have to mention that I really enjoy listening to Lex Fridman’s podcasts.

Aishwarya Kshirsagar

I am pursuing a Master’s degree in Visual Computing at Saarland University. My main
interests have been in the areas of Computer Vision and Deep Learning.

I completed my Bachelor’s degree from Pune University where I focused on Machine Learning as well as Image Processing. Currently, I am supporting the 3D Computer Vision Lecture at CVMP Lab.

In my free time, I enjoy traveling, cooking, and also listening to podcasts.

Kunwar Singh

I am a masters student at Saarland university. I am interested in RGBD non-rigid reconstruction systems.

I did my Bachelors from IIIT-Hyderabad, India, where I explored fusion methods and camera calibration setups.

I am currently gathering and processing data for the 3D Computer Vision course at CVMP.

Jan Eric Lenssen

I am a postoctoral researcher at MPI for Informatics in Saarbrücken since 2021 and since recently leader of the Geometric Representation Learning Group. I obtained my PhD in computer science at TU Dortmund University and did research internships at Facebook Reality Labs and Nnaissense.

My research interests are differentiable algorithms and representations for encoding and processing of 3D data, mostly aligned towards the overall goal of 3D from 2D images. My main contributions lie in the areas of graph neural networks, neural fields and point-based representations. I collaborate with the CVMP group on research projects in these areas.

Philipp Schröppel

I am a PhD student under the supervision of Prof. Thomas Brox in the Computer Vision Group at the University of Freiburg since 2019. 

My main research interest is 3D reconstruction from images in terms of 3D geometry, ego-motion and object motion with particular focus on robust application of arbitrary real-world data. 

To this end, I develop and maintain the Robust Multi-View Depth (robustmvd) framework for depth estimation from multiple input views with a focus on robust application independent of the target data. 

Currently, I am working together with the CVMP lab on generative modeling of 3D scenes, with the main objective of learning priors to enhance and complete 3D reconstructions.

Christopher Wewer

Since 2022, I am a PhD student in the Computer Vision and Machine Learning group at the Max Planck Institute for Informatics, advised by Prof. Bernt Schiele. I further collaborate with Dr. Jan Eric Lenssen and Prof. Eddy Ilg.

My research focuses on 3D reconstruction and generation. For example, we investigated the idea of learning category specific self-similarities in an unsupervised fashion, which can be leveraged as a minimal required data prior for 3D reconstruction from as few as a single view.

Besides 3D reconstruction, I am currently involved in several collaborations exploring 3D generation. Following the recent success of diffusion models for image generation, we are working on adaptations for generation of 3D objects or entire scenes.

Adam Kortylewski

Adam Kortylewski is a research group leader at the University of Freiburg and the Max Planck Institute for Informatics where he leads the Generative Vision and Robust Learning lab. Before that he was a postdoc at Johns Hopkins University with Alan Yuille for three years. He obtained his PhD from the University of Basel with Thomas Vetter. His research focuses understanding the principles that enable artificial intelligence systems to reliably perceive our world through images. Adam was awarded the prestigious Emmy Noether Grant (2022) of the German Science Foundation for exceptionally qualified early career researchers.

Adam collaborates with the CVMP lab in the area of generative vision and co-supervises Navdeep Singh and Tom Fischer.

Mona Linn

I am supporting the CVMP lab as an administrative assistant with procurement, accounting, and recruiting. Please contact me if you like to get in touch with the lab and for general inquiries.

Kevin Raj

I completed my Master’s in Visual Computing at Saarland University in March 2024. My broad interests lie in the intersection of Computer Vision, Computer Graphics, and Machine Learning. During my time in the lab, I investigated techniques for uncertainty in 3D representations under the supervision of Professor Eddy Ilg.

Before coming to Saarland, I worked as a Research Assistant at the Indian Insititute of Science, Bangalore, under the supervision of Dr. Chandra Sekhar. My work was related to Biomedical image processing using deep learning and signal/image processing techniques. I did my Bachelor’s in Electrical and Electronics at Manipal Institute of Technology, Manipal, from 2015-2019.

Generally, I spend my free time watching anime, traveling, and cooking 🙂

Devikalyan Das

I completed my Master’s in Visual Computing at Saarland University. My interests lie in Computer Graphics, Computer Vision, and Machine Learning, with the aim of better understanding of the world around me from the eyes of the computer.

I did my master’s thesis under the supervision of Professor Eddy Ilg, where I am focussing on the efficient 3D reconstruction of deformable objects in video.

I enjoy cooking, playing flute, and swimming or jogging during my free time

Tomas Amado

I was a Data Science and Artificial Intelligence Master’s student at Saarland University. My interests have been in the areas of computer vision, machine learning, and recently 3D computer vision.

I wrote my Master’s thesis with Professor Ilg focusing on the topic of using Slot Attention mechanisms to learn Object-centric representations from 3D Point Cloud data.

I studied my Bachelor’s in Computer Engineering at Rafael Urdaneta University from 2016-2019 in my home city of Maracaibo, Venezuela mainly focusing on software engineering, and have been since 2020 living in Germany and doing my Master’s at Saarland University.

In my free time, I mostly do sports like volleyball, running, and bouldering. I also love playing the guitar and exploring new music everytime I can.

Suraj Sudhakar

I joined CVMP as a new Hiwi in October 2022.

I completed my Master’s in Visual Computing at Saarland University and did my Bachelor’s in Electronics & Communication at the BMS College of Engineering, Bangalore, from 2014-2018. My research interests lie in the area of Computer Vision & Deep Learning. More specifically, I am interested in explainable models which have a well-rooted theory behind them.

In my Hiwi, I helped Professor Ilg set up the datasets, and the environment necessary to enable smooth research. I was also responsible for handling minor changes to the website. The lab’s research is in my area of interest such as 3D representations and explainable neural networks and I look forward to researching work in the lab.

I enjoy watching anime and playing games. I am also learning to cook!

Nikhil Paliwal

I was a Master’s student at Saarland University, studying in the Data Science and Artificial Intelligence program. I have a background in self-supervision, model compression techniques, and deep learning. I did my bachelor’s in Communication and Computer Engineering from the LNM Institute of Information Technology, India from 2015-19. I also received Chairman’s gold medal for best overall performance in graduating batch.

I am aiming towards making deep learning more accessible by reducing the requirement for large amounts of supervised labels, reducing computational resource needs, and catastrophic forgetting in continual systems. In my master’s thesis, I focused on the topic of knowledge transfer with continual learning.

In my leisure time, I enjoy activities such as football and swimming. I also enjoy science fiction, reading novels, and watching movies.