Bonjour à tous,
j'ai fait déplacer un cours d'électronique du mercredi 13/12 après-midi (ce sera effectif très vite) pour vous permettre d'assister au séminaire ci-dessous.
En tant qu'étudiants en IA, il vous est fortement conseillé d'y assiter :
----
Bonjour à tous,
Nous avons le plaisir de vous inviter à un séminaire du laboratoire COSMER le mercredi 13/12/2023 à 14h00 dans l'amphi du batiment M qui se déroulera en anglais.
Notre invité, Vincent Lepetit , Professeur à l'ENPC ParisTech, nous présentera un séminaire sur :
- Title:
Self-Supervised 3D Scene Understanding - Abstract:
I will present our recent work on how a general AI algorithm can be used for 3D scene understanding to reduce the need for training data. More exactly, we propose several modifications of the Monte Carlo Tree Search (MCTS) algorithm to retrieve objects and room layouts from noisy RGB-D scans. While MCTS was developed as a game-playing algorithm, we show it can also be used for complex perception problems. Our adapted MCTS algorithm has few easy-to-tune hyperparameters and can optimise general losses. We use it to optimise the posterior probability of objects and room layout hypotheses given the RGB-D data. This results in a render-and-compare method that explores the solution space efficiently. I will then show that the same algorithm can be applied to other scene understanding problems with RGB data only. - Bio:
I am a professor at ENPC ParisTech, France. Before that, I was a full professor at the Institute for Computer Graphics and Vision, TU Graz, Austria and before that, a senior researcher at CVLab, EPFL, Switzerland.
My research focuses on 3D scene understanding. More exactly, I aim at reducing as much as possible the guidance a system needs to learn new 3D objects and new 3D environments: How can we remove the need for training data for each new 3D problem? Currently, even self-supervised methods often require CAD models, which are not necessarily available for any type of object. This question has both theoretical implications and practical applications, as the need for training data, even synthetic, is often a deal breaker for non-academic problems.
I received the Koenderick “test-of-time” award at the European Conference on Computer Vision 2020 for “Brief: Binary Robust Independent Elementary Features”. I often serve as an area chair of the major computer vision conferences: CVPR, ICCV, ECCV, ACCV, BMVC and as an editor for PAMI and IJCV.
Bien à vous,