Jannik Endres

Hi, I’m Jannik! I am a PhD student in computer science supervised by Radu Timofte. My research focuses on computer vision, machine learning, and robotics.

Previously, I was a research intern at Mila - Quebec AI Institute under the supervision of David Rolnick, Etienne Laliberté, and Arthur Ouaknine, where I worked on computer vision for forest monitoring. Prior to that, I conducted research on omnidirectional stereo matching supervised by Alexandre Alahi, Simone Schaub-Meyer, Charles Corbière, Oliver Hahn, and Stefan Roth.

I received my M.Sc. in Computational Engineering and B.Sc. in Electrical Engineering and Information Technology, both from TU Darmstadt. During my studies, I also spent time as an exchange student at EPFL.

News

Jul 04, 2026	Our paper “Estimating Individual Tree Height and Species from UAV Imagery” has been accepted at ECCV 2026!

Selected Publications

ECCV 2026

Estimating Individual Tree Height and Species from UAV Imagery

Jannik Endres, Etienne Laliberté, David Rolnick, and Arthur Ouaknine

In Proceedings of the European Conference on Computer Vision, 2026

Abs arXiv PDF Code Benchmark Project Page

Accurate estimation of forest biomass, a major carbon sink, relies heavily on tree-level traits such as height and species. Unoccupied Aerial Vehicles (UAVs) capturing high-resolution imagery from a single RGB camera offer a cost-effective and scalable approach for mapping and measuring individual trees. We introduce BIRCH-Trees, the first benchmark for individual tree height and species estimation from tree-centered UAV images, spanning three datasets: temperate forests, tropical forests, and boreal plantations. We also present DINOvTree, a unified approach using a Vision Foundation Model (VFM) backbone with task-specific heads for simultaneous height and species prediction. Through extensive evaluations on BIRCH-Trees, we compare DINOvTree against commonly used vision methods, including VFMs, as well as biological allometric equations. We find that DINOvTree achieves top overall results with accurate height predictions and competitive classification accuracy while using only 54% to 58% of the parameters of the second-best approach.
IROS 2025

Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model

Jannik Endres, Oliver Hahn, Charles Corbière, Simone Schaub-Meyer, Stefan Roth, and Alexandre Alahi

In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2025

Abs arXiv PDF Code Video Poster Project Page

Omnidirectional depth perception is essential for mobile robotics applications that require scene understanding across a full 360° field of view. Camera-based setups offer a cost-effective option by using stereo depth estimation to generate dense, high-resolution depth maps without relying on expensive active sensing. However, existing omnidirectional stereo matching approaches achieve only limited depth accuracy across diverse environments, depth ranges, and lighting conditions, due to the scarcity of real-world data. We present DFI-OmniStereo, a novel omnidirectional stereo matching method that leverages a large-scale pre-trained foundation model for relative monocular depth estimation within an iterative optimization-based stereo matching architecture. We introduce a dedicated two-stage training strategy to utilize the relative monocular depth features for our omnidirectional stereo matching before scale-invariant fine-tuning. DFI-OmniStereo achieves state-of-the-art results on the real-world Helvipad dataset, reducing disparity MAE by approximately 16% compared to the previous best omnidirectional stereo method.