David Recasens

PhD researcher in 3D Computer Vision and Machine Learning with background in Gaussian Splatting, 3D reconstruction, depth estimation, SLAM and generative AI. Experienced across top research labs (NVIDIA, Disney, Meta, Huawei, ETH CVG) driving novel methods in robotics, AR/VR, and medical imaging.

Completed PhD under the guidance of Prof. Javier Civera at the Robotics Lab in the Universidad de Zaragoza in December 2025. I did a research stay at Computer Vision and Geometry Group (CVG) directed by Prof. Marc Pollefeys in ETH Zurich, Switzerland, supervised by Martin. R. Oswald from September 2021 to March 2022.

I interned as Research Scientist at Huawei Research Center (Jan–Jul 2024), Meta Reality Labs (Jul 2024–Mar 2025) and Disney Research (Mar–Jun 2025), all in Zurich, Switzerland. Currently, I am a Robotics Software intern at NVIDIA in Zurich.

Email  /  LinkedIn  /  Google Scholar  /  GitHub

PAGaS refines per-view depth maps using pixel-aligned Gaussians that carry a single degree of freedom along their viewing ray, uses only photometric constraints from a few adjacent views and captures unprecedented pixel-level detail in both object-centric and large-scale scenes.

The Drunkard’s Dataset, a challenging collection of synthetic data targeting visual navigation and reconstruction in deformable environments. And the Drunkard’s Odometry, a novel monocular RGB-D deformable odometry method that breaks down optical flow estimate into rigid-body camera motion and non-rigid scene deformation.

Deepening for the first time in Bayesian deep networks for single-view depth estimation in colonoscopies.

A pipeline that estimates the 6-degrees-of-freedom camera pose and dense 3D scene models from monocular endoscopic videos.

First collection of complete endoscopy sequences acquired during regular medical practice to support the development visual SLAM methods.

Based on the Jon Barron's template.