Janick Martinez Esturo

I am a Principal Research Engineer at the NVIDIA Spatial Intelligence Lab (SIL) in Munich.

I am interested in the geometric, computational, and probabilistic aspects of challenging Computer Vision, Robotics, Computer Graphics, and Visualization problems. In particular, my research background includes interactive tools for shape modeling/editing, geometry-based flow visualization, localization from heterogeneous data, self-calibration of automotive sensors, and neural scene reconstruction.

Recent publications

	Turki, H., Wu, Q., Kang, X., et al. SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms Proc. ICLR. 2026 [pdf] [project] [arXiv] [video] [details]
	Wu, Q., Martinez Esturo, J., Mirzaei, A., Moenne-Loccoz, N., and Gojcic, Z. 3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting Proc. CVPR. 2025 [pdf] [code] [project] [arXiv] [video] [details]
	Chen, Z., Yang, J., Huang, J., et al. OmniRe: Omni Urban Scene Reconstruction Proc. ICLR (Spotlight). 2025 [pdf] [code] [project] [arXiv] [video] [details]
	Moenne-Loccoz, N., Mirzaei, A., Perel, O., et al. 3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes ACM Trans. Graph. (Proc. SIGGRAPH Asia) 43, 6. 2024 [pdf] [code] [project] [arXiv] [video] [details]

All publications

News

Jul 2026: Technical report Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation is out.
Jan 2026: Started as Principal Research Engineer at the NVIDIA Spatial Intelligence Lab.
Jun 2025: 3DGUT presented at CVPR 2025.
Dec 2024: 3D Gaussian Ray Tracing presented at SIGGRAPH Asia 2024.
Oct 2014: Best Paper Award at VMV 2014 for Pattern Search in Flows.