3D Computer Vision & Generative modelling
PhD student @ Inria Paris & @valeoai.bsky.social | Researcher @ Ukrainian Catholic University
https://t-martyniuk.github.io/
Ivan is presenting his results on Materials, Geometry, and Semantics Estimation for scene understanding and editing.
Papers: Material Palette, Material Transform and MatSwap (Materials) & StableMTL and DenseMTL (Multi-task learning).
Ivan is presenting his results on Materials, Geometry, and Semantics Estimation for scene understanding and editing.
Papers: Material Palette, Material Transform and MatSwap (Materials) & StableMTL and DenseMTL (Multi-task learning).
His thesis «Learning Actionable LiDAR Representations w/o Annotations» covers the papers BEVContrast (learning self-sup LiDAR features), SLidR, ScaLR (distillation), UNIT and Alpine (solving tasks w/o labels).
His thesis «Learning Actionable LiDAR Representations w/o Annotations» covers the papers BEVContrast (learning self-sup LiDAR features), SLidR, ScaLR (distillation), UNIT and Alpine (solving tasks w/o labels).
But let me just tell you: I feel like I’m at a wedding in Bukovyna rn, and I mean it in the best way possible! Such an amazing reception and beautiful Romanian folk music :) #iv2025
But let me just tell you: I feel like I’m at a wedding in Bukovyna rn, and I mean it in the best way possible! Such an amazing reception and beautiful Romanian folk music :) #iv2025
Project page: astra-vision.github.io/LiDPM/
w/ @gillespuy.bsky.social, @alexandreboulch.bsky.social, Renaud Marlet, Raoul de Charette
Also, see our poster at 3pm in the Caravaggio room and AMA 😉
Project page: astra-vision.github.io/LiDPM/
w/ @gillespuy.bsky.social, @alexandreboulch.bsky.social, Renaud Marlet, Raoul de Charette
Also, see our poster at 3pm in the Caravaggio room and AMA 😉
#IV2025
#IV2025
Today is the Workshops day.
#autonomousDriving #autonomousVehicles #computerVision #AI
Today is the Workshops day.
#autonomousDriving #autonomousVehicles #computerVision #AI
Next stop: #IV2025.
Next stop: #IV2025.
tldr: LiDPM enables high-quality LiDAR completion by applying a vanilla DDPM with tailored initialization, avoiding local diffusion approximations.
Project page: astra-vision.github.io/LiDPM/
tldr: LiDPM enables high-quality LiDAR completion by applying a vanilla DDPM with tailored initialization, avoiding local diffusion approximations.
Project page: astra-vision.github.io/LiDPM/
What do your feeds look like?
What do your feeds look like?