Marco Schouten
I am a PhD student at the Pioneer Centre for AI (Belongie Lab) in Copenhagen. I am fortunate to be advised by Prof Dim Papadopoulos and Prof Serge Belongie. I am a visiting researcher in Prof David Picard (Imagine Lab) at École nationale des ponts et chaussées in Paris. Previously, I was a research scientist intern at Adobe Research working in Prof Tamy Boubekeur's team, and a research intern at the KTH Maritime Robotics Laboratory, advised by Prof John Folkesson. I was also an exchange student at TU Delft in Prof R.R. Venkatesha Prasad group. In my free time, I enjoy drawing.
I am on the job market for 2027.
Selected Publications
I have a background in computer science, machine learning, vision, graphics, and robotics. I am specialising in efficient and controllable generative modelling (diffusion models, LLMs, Agents) for 2D and 3D visual data.
|
HiddenObjects: Diffusion-Distilled Dense Spatial Priors for Object Placement Marco Schouten, Ioannis Siglidis, Serge Belongie and Dim P. Papadopoulos WACV, 2027 |
|
MeshQuery: Agentic Seam Planning for UV Parametrization Marco Schouten, Arthur Roullier, Elie Michel, Ruben Wiersma, Axel Paris and Tamy Boubekeur Preprint, 2026 (Work done at Adobe) |
|
EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground Truth Jens Parslov, Marco Schouten and Dim P. Papadopoulos NeurIPS, 2026 |
|
Sherlock Your Queries: Learning to Ask the Right Questions for Dialogue-Based Retrieval Dong Yun*, Marco Schouten* and Dim P. Papadopoulos (* equal contribution) Preprint, 2025 |
|
POEM: Precise Object-level Editing via MLLM control Marco Schouten, M. Onurcan Kaya, Serge Belongie and Dim P. Papadopoulos SCIA, 2025; CVEU Workshop @ CVPR 2025 |
Experience
-
Pioneer Centre for AI (Belongie Lab)
PhD Student
Generative modelling for image generation and editing.
-
École nationale des ponts et chaussées (Imagine Lab)
Visiting Researcher
Generative modelling for image generation and editing.
-
-
-
KTH Royal Institute of Technology (Maritime Robotics Laboratory)
Research Intern
SLAM for underwater robotics.
-
Delft University of Technology
Visiting Student Researcher
Imitation learning for skill transfer in human-robot teleoperation.