Marc Benedí San Millán

Marc Benedí San Millán

PhD Candidate @ Visual Computing Group

Technische Universität München

👋 Hola! Hello! Hallo!

I am a PhD candidate at Matthias Nießner’s Visual Computing Group, at the Technical University of Munich.

I’m interested in computer vision, deep learning and optimization. My research is mostly focused on robust correspondence estimation for rigid 3D reconstruction.

Before joining the group, I received a Master’s Degree in Computer Science from the Technical University of Munich and a Bachelor’s Degree in Computer Science from the Polytechnical University of Catalonia.


Visual Computing & Artificial Intelligence Lab, Technische Universität München
Research Fellowship
April 2021 – March 2022 Munich, DE
  • Fellowship awarded to outstanding Master students to allow them developing state-of-the-art models. See page.
  • See project’s page.
Visual Computing & Artificial Intelligence Lab, Technische Universität München
Working Student
April 2020 – September 2022 Munich, DE
  • Built a high-performance GPU cluster for the Deep Learning laboratory.
  • Built a frontend with Vue.js and a backend for the cluster’s users.
HELM Mobile Development
Software Engineer
September 2018 – September 2019 Barcelona, ES
  • Android development with Kotlin.
  • Backend development with Kotlin.
  • Frontend development with Vue.js
European Organization for Nuclear Research (CERN)
June 2018 – September 2018 Geneva, CH
  • Designed and built a cluster for the BE-OP-LHC team at CERN using Kubernetes.
Polytechnical University of Catalonia, Barcelona Tech
Research Assistant
September 2017 – January 2018 Barcelona, ES
  • Worked on a novel conversion of Binary Decision Trees to Conjunctive Normal Forms.
  • See project’s page.
Ernst & Young
June 2017 – September 2017 Barcelona, ES
  • Frontend and backend development.
Android Instructor
January 2017 – January 2017 Barcelona, ES
  • Taught a two-week course to introduction to Android development to 25+ students.


Learning Correspondences For Relative Pose Estimation
We present an end-to-end learnable, differentiable method for pairwise relative pose registration of RGB-D frames. Our method is robust to big camera motions thanks to a self-supervised weighting of the predicted correspondences between the frames. Given a pair of frames, our method estimates matches of points and their visibility score. A self-supervised model predicts a confidence weight for visible matches. Finally, visible matches and their weight are fed into a differentiable weighted Procrustes aligner which estimates the rigid transformation between the input frames.
Kinect Fusion: Dense Surface Mapping and Tracking
Implementation of the paper “Kinect Fusion: Real-Time Dense Surface Mapping and Tracking”
SLAM for autonomous vehicles
In this project, I worked on the SLAM pipeline for an autonomous driving vehicle. The tools I used for this project are, ROS, C++, PCL library, Ceres Solver, and Google Cartographer.
Divergence-Free Shape Correspondence with Time Dependent Vector Fields
In this project, we extended the work of Eisenberger, Zorah, Cremers, “Divergence-Free Shape Interpolation and Correspondence” 1. In their work, they present a method to calculate deformation fields between shapes embedded in $\mathbb{R}^D$.
Design of an environment for solving pseudo-Boolean optimization problems
Bachelor’s thesis Boolean Satisfiability problems (SAT) consists of finding a valid assignment (model) for a set of Boolean variables. It was the first problem proven to be NP-Complete which allowed reducing many NP-Complete problems to it.
StirHack 2016
Writing about StirHack16, the first hackathon I ever attended, brings me very good memories. In this page I will focus on the project itself, although some day I should write about the hackathon experience.


Don't hesitate to reach out in any of the following ways!