Title: Deep generative models for weakly-supervised improvement of photogrammetric models
Contact: Maxime Lhuillier (chargé de recherches CNRS, HDR) [email protected]
Keywords: deep generative models, semi-supervised learning, surface reconstruction from images, photogrammetry for VR.
Summary:
The 3D reconstruction of a complete environment from images is useful in a lot of applications including virtual reality (https://maximelhuillier.fr) and perception of autonomous vehicles.
Several methods of computer vision and photogrammetry are needed to solve this problem.
They include the estimation of the geometry (camera parameters and cloud of 3D points) from images and the surface reconstruction.
A promising way of research is the design of deep learning methods that improve the surface reconstruction step.
We also would like to avoid supervised methods, which need dataset of environments generated by 3D scanner.
There are several reasons to do this: price/availability/experimental conditions of the scanner and time/effort of acquisition.
Thus we replace dataset obtained by 3D scanner by other dataset.
The dataset can be synthetic and collect surface segments that are known to be very probable in the environments.
The dataset can also include large environments reconstructed by a previous method (which is not deep learning), with a minority of manual corrections.
Then a network learns to replace a wrong or improbable segment of surface by a more probable one.
Thanks to the learning, we expect to improve previous surface reconstruction methods, for example when experimental conditions are difficult.
Two kinds of deep learning methods can potentially do this.
The non-generative methods (eg autoencoder) compute only one result, ie one corrected surface.
They have drawbacks: uncertainty of the result is unknown and user cannot choose the best among several results.
The generative methods (eg variational autoencoder or diffusion model) can remove these drawbacks since they provide several results, more precisely a distribution of results.
In experiment, we focus on complete outdoor environments reconstructed by using a 360 camera (fixed on a helmet or a vehicle) that moves hundreds of meters or more.
Short bibliography:
- J.Ho, A.Jain, P.Abbeel, Denoising diffusion probabilistic models, NeurIPS 2020.
- D.P.Kingma, M.Welling, Auto-encoding variational Bayes, ICLR 2014.
- M.Lhuillier, Surface reconstruction from a sparse point cloud by enforcing visibility consistency and topology constraints, CVIU 175, 2018.
- M.Lhuillier, Estimating the vertical direction in a photogrammetric 3D model, with application to visualization, CVIU 236, 2023.
- S.Peng, M.Niemeyer, L.Meschender, M.Pollefeys, A.Geiger, Convolutional occupancy networks, ECCV 2020.
- M.Prakash, A.Krull, F.Jug, Fully unsupervised diversity denoising with convolutional variational autoencoders, ICLR 2021.
- Y.Song, S.Ermon, Generative modeling by estimating gradients of the data distribution, NIPS 2019.
- R.Sulzer, L.Landrieu, R.Marlet, B.Vallet, Scalable surface reconstruction with Delaunay-graph neural networks, CGF 40(5) 2021.
Application:
Send a CV, transcripts (including scores and ranks) of BSc and MSc, motivation letter and recommendation letter(s) to [email protected] before Tuesday 30th April 2024.
Requirements: master's degree or engineer's degrees in 2024 or before, mathematical background (probability, statistics, linear algebra, optimization), programming skills in Python and Pytorch, knowledge in photogrammetry/computer vision is a plus.
Contract:
3-year contract started on october 2024, in the ComSee team at the Institut Pascal, Clermont-Ferrand, France.
Similar Positions
-
Postdoctoral Research Associate In Time Series Analysis, University of Oxford, United Kingdom, 4 days ago
We look for an enthusiastic researcher to join the interdisciplinary team studying why elephants use seismic communication. The project, under the leadership of Dr Beth Mortimer, leverages a uniqu...
-
Post Doctoral Research Position Predicting Environmental Changes Using Deep Learning, Satellite Remote Sensing And Future Climate Projections. Case Studies In Southern Kenya And The Brazilian Amazon W/M, IRD Occitanie, France, about 1 month ago
27 Mar 2024 Job Information Organisation/Company IRD Occitanie Research Field Environmental science Researcher Profile First Stage Researcher (R1) Country France Application Deadline 27 Apr 2024 -...
-
Post Doctoral Chemical & Biological Engineering (Machine Vision), University of Saskatchewan, Canada, 5 days ago
Dr. Oon-Doo Baik and collaborators are currently seeking a postdoctoral fellow to join an exciting research project. The focus of this project is to develop a machine vision system to assess sprou...
-
Postdoctoral Research Associate , ; University of Oxford, United Kingdom, 23 minutes ago
About the role This postdoc position will be part of an exciting project exploring the principles of biodiversity and sustainability with an emphasis on quantifying large mammal movement, decision...
-
Postdoctoral Fellow In Biomedical Optics And Medical Physics, UT southwestern medical center-faculty of medical physics, United States, 11 days ago
We are looking for skilled and enthusiastic candidates to fill Postdoctoral Fellow positions in the Biomedical Imaging and Radiation Technology Laboratory (BIRTLab). Our mission is to innovate, de...
-
Postdoctoral Research Scholar In Planetary Field Geology, Arizona State University, School of Earth and Space Exploration, United States, about 12 hours ago
The Dreamscape Discovery Initiative (DDI) and the School of Earth and Space Exploration (SESE) at Arizona State University invite applications for a Postdoctoral Research Scholar in Planetary Fiel...