Adrien Kaiser

I am an R&D Engineer in the Research & Labs team of Adobe 3D & AR in Paris.
I am applying Computer Vision and Machine Learning to digital material acquisition for the Substance texturing ecosystem.
I obtained my PhD thesis in 2019 from the Computer Graphics group at Telecom Paris, France, supervised by Prof. Tamy Boubekeur.

News

2020 / 08 / 27Our patent on depth image registration was published.
2020 / 04 / 01  I joined Adobe 3D & AR in Paris, working on digital material acquisition for the Substance texturing ecosystem.
2020 / 01 / 20Our preprint on plane-based 3D view registration is online.
2019 / 07 / 01  I successfully defended my PhD thesis at Telecom Paris.
2019 / 05 / 06-10 EUROGRAPHICS 2019, Genova, Italy: Presentation of our survey on Simple Geometric Primitive Fitting for Captured 3D Data.
2019 / 02 / 28Invited talk on Proxy Clouds for the research seminar of NPM3D class in MVA master of ENS Paris-Saclay at Mines ParisTech.
2019 / 01 / 16Our Survey on Simple Geometric Primitive Fitting has been invited for presentation at EUROGRAPHICS 2019.
2018 / 10 / 22Invited talk at the IMAGINE research group of ENPC about Simple Geometric Primitives for Captured 3D Data.
2018 / 10 / 11Research Day of the LTCI research center of Telecom ParisTech.
2018 / 09 / 08-14   ECCV 2018, Munich, Germany: Poster for full paper on Proxy Clouds.
2018 / 07 / 05 Research Day of the "Image, Signal, Data" department: Talk on Proxy Clouds.
2018 / 07 / 04The webpage for our Survey on Simple Geometric Primitive Fitting is up.
2018 / 07 / 03  Our full paper on Proxy Clouds for Live RGB-D Stream Processing and Consolidation has been accepted for publication at ECCV 2018.
2018 / 06 / 25Ending presentation for the 2018 IGR205 project at Telecom ParisTech.
2018 / 06 / 07PhD training on Ethics for Information Technology.
2018 / 05 / 17Presentation of the article PointNet to the CG group.
2018 / 05 / 14  Our Survey on Simple Geometric Primitive Fitting has been accepted for publication in Computer Graphics Forum.
2018 / 04 / 26Beginning of the 2018 IGR205 project at Telecom ParisTech.
2018 / 02 / 15Young researchers night of the Paris ACM SIGGRAPH chapter.
2017 / 11 / 23Presentation of the article 3DLite to the CG group.
2017 / 11 / 16PhD training on Patents and Intellectual Property.
2017 / 10 / 10Research Day of the LTCI research center of Telecom ParisTech.
2017 / 07 / 30-03   SIGGRAPH 2017, Los Angeles, USA: Technical Talk on Proxy Clouds for RGB-D Stream Processing.
2017 / 07 / 06 Research Day of the "Image, Signal, Data" department: Presentation of a poster on Proxy Clouds for RGB-D Stream Processing.
2017 / 07 / 04 PhD mid-term evaluation by Dr. Eric Lecolinet and Dr. Mathieu Bredif.
2017 / 06 / 08-10Futur En Seine 2017, Paris, France: Presentation of Ayotle's Hayo camera.
2017 / 05 / 05-29PhD training on Scientific Presentation at Telecom ParisTech.
2017 / 05 / 03-31Following computational geometry lectures from Prof. Jean-Daniel Boissonnat at the College de France.
2017 / 04 / 24  Our insight technical talk on Proxy Clouds for RGB-D Stream Processing has been accepted at SIGGRAPH 2017.
2017 / 04 / 24-28 EUROGRAPHICS 2017, Lyon, France: Presentation of a preview poster on Proxy Clouds for RGB-D Stream Processing.
2017 / 04 / 20Presentation of an article on Automatic Building Modeling from Point Clouds to the CG group.
2017 / 03 / 22-25Laval Virtual 2017, Laval, France: Presentation of Ayotle's Hayo camera.
2017 / 03 / 04Our preview poster on Proxy Clouds for RGB-D Stream Processing has been accepted for presentation at EUROGRAPHICS 2017.
2017 / 02 / 23Presentation of my work on Proxy Clouds for RGB-D Stream Processing to the CG group.
2017 / 02 / 08Launch of the Indiegogo campaign for Ayotle's Hayo camera.
2017 / 01 / 30Ending presentation for the EPITA PFEE project.
2016 / 11 / 10 Welcome Day for new PhD students: Presentation of a poster on my recent research work and live demo of the Hayo camera.
2016 / 10 / 13Presentation of my work on Live Capture of 3D Geometric Primitives to the CG group.
2016 / 10 / 06Launch of the website for Ayotle's Hayo camera: hayo.io
2016 / 06 / 27Ending presentation for the IGR205 project at Telecom ParisTech.
2016 / 05 / 19Beginning of the IGR205 project at Telecom ParisTech.
2016 / 05 / 11Beginning of the EPITA PFEE project with Ayotle.
2016 / 04 / 19Presentation of my surveying work on Simple Geometric Primitive Fitting to the CG group.
2016 / 02 / 18Presentation of the article "DynamicFusion" to the CG group.
2015 / 12 / 01  I started my PhD within the Computer Graphics group at Telecom ParisTech.

Research Interests

Computer vision, Scene analysis, Spatial reasoning
Geometric modeling
Simultaneous Localization and Mapping (SLAM), Robotics
Real-time systems, Embedded systems

Background

2020 - R&D engineer at Adobe 3D & AR / SubstanceParis, FranceCurrent
2015 - 2020Research engineer at Ayotle SASParis, France4.5 years
2015 - 2019PhD candidate at Telecom ParisParis, France3.5 years
2014 - 2015Software engineer at CorexpertLyon, France10 months
2014Computer Vision intern at Wikitude GmbHSalzburg, Austria8 months
2013 - 2014Master of Science by Research at the University of LyonLyon, France12 months
2012 - 2013Research intern at the University of North CarolinaChapel Hill, NC, USA12 months
2011Intern at Thales AvionicsValence, France1 month
2010 - 2014Diplome d'Ingenieur (MSc in EECS) at CPE LyonLyon, France4 years
2008 - 2010Preparatory Classes for CPE LyonLyon, France2 years

Projects and Publications

             

October 2015
May 2019

Real-Time Scene Analysis for 3D Interaction

 

PhD Thesis. Work done at Telecom Paris in collaboration with Ayotle SAS.
Collaborators: Prof. Tamy Boubekeur, Dr. Jose Alonso Ybanez Zepeda

Keywords: Visual scene analysis, Commodity depth sensors, Geometric analysis, High level abstraction

This PhD thesis focuses on the problem of visual scene analysis captured by commodity depth sensors to convert their data into high level understanding of the scene. It explores the use of 3D geometry analysis tools on visual depth data in terms of enhancement, registration and consolidation. In particular, we aim to show how shape abstraction can generate lightweight representations of the data for fast analysis with low hardware requirements. This last property is important as one of our goals is to design algorithms suitable for live embedded operation in e.g., wearable devices, smartphones or mobile robots. The context of this thesis is the live operation of 3D interaction on a mobile device, which raises numerous issues including placing 3D interaction zones with relation to real surrounding objects, tracking the interaction zones in space when the sensor moves and providing a meaningful and understandable experience to non-expert users. Towards solving these problems, we make contributions where scene abstraction leads to fast and robust sensor localization as well as efficient frame data representation, enhancement and consolidation. While simple geometric surface shapes are not as faithful as heavy point sets or volumes to represent observed scenes, we show that they are an acceptable approximation and their light weight makes them well balanced between accuracy and performance.

September 2017
November 2018

Plane Pair Matching for Efficient 3D View Registration

 

Work done during my PhD at Telecom Paris in collaboration with Ayotle SAS.
Collaborators: Prof. Tamy Boubekeur, Dr. Jose Alonso Ybanez Zepeda

Keywords: RGB-D images, Registration, Localization, Plane pairs, Scene structure

We present a novel method to estimate the motion matrix between overlapping pairs of 3D views in the context of indoor scenes. We use the Manhattan world assumption to introduce lightweight geometric constraints under the form of planes into the problem, which reduces complexity by taking into account the structure of the scene. In particular, we define a stochastic framework to categorize planes as vertical or horizontal and parallel or non-parallel. We leverage this classification to match pairs of planes in overlapping views with point-of-view agnostic structural metrics. We propose to split the motion computation using the classification and estimate separately the rotation and translation of the sensor, using a quadric minimizer. We validate our approach on a toy example and present quantitative experiments on a public RGB-D dataset, comparing against recent state-of-the-art methods. Our evaluation shows that planar constraints only add low computational overhead while improving results in precision when applied after a prior coarse estimate. We conclude by giving hints towards extensions and improvements of current results.

  A. Kaiser, J.A. Ybanez Zepeda and T. Boubekeur:
Plane Pair Matching for Efficient 3D View Registration
ArXiv 2020     

  A. Kaiser, J.A. Ybanez Zepeda, T. Boubekeur and A. Courteville:
Method for Registering Depth Images
WO 2020/169381 A1 (priority date 2019-02-22)   

September 2016
March 2018

Proxy Clouds for Live RGB-D Stream Processing and Consolidation

Work done during my PhD at Telecom Paris in collaboration with Ayotle SAS.
Collaborators: Prof. Tamy Boubekeur, Dr. Jose Alonso Ybanez Zepeda

Keywords: RGB-D images, Scene analysis, Geometric analysis, 3D point cloud, 3D geometric primitives, planes, Data accumulation, High level superstructure, Live processing, Depth improvement, Data reinforcement, Scene reconstruction, 3D data compression

We propose a new multiplanar superstructure for unified real-time processing of RGB-D data. Modern RGB-D sensors are widely used for indoor 3D capture, with applications ranging from modeling to robotics, through augmented reality. Nevertheless, their use is limited by their low resolution, with frames often corrupted with noise, missing data and temporal inconsistencies. Our approach, named Proxy Clouds, consists in generating and updating through time a single set of compact local statistics parameterized over detected planar proxies, which are fed from raw RGB-D data. Proxy Clouds provide several processing primitives, which improve the quality of the RGB-D stream on-the-fly or lighten further operations. Experimental results confirm that our light weight analysis framework copes well with embedded execution as well as moderate memory and computational capabilities compared to state-of-the-art methods. Processing of RGB-D data with Proxy Clouds includes noise and temporal flickering removal, hole filling and resampling. As a substitute of the observed scene, our proxy cloud can additionally be applied to compression and scene reconstruction. We present experiments performed with our framework in indoor scenes of different natures within a recent open RGB-D dataset.

  A. Kaiser, J.A. Ybanez Zepeda and T. Boubekeur:
Proxy Clouds for RGB-D Stream Processing: A Preview
EUROGRAPHICS 2017 - Posters Program     

  EUROGRAPHICS 2017, April 24-28, Lyon, France  

  A. Kaiser, J.A. Ybanez Zepeda and T. Boubekeur:
Proxy Clouds for RGB-D Stream Processing: An Insight
ACM SIGGRAPH 2017 - Talks Program       

  ACM SIGGRAPH 2017, July 30 - August 3, Los Angeles, CA, USA  

  A. Kaiser, J.A. Ybanez Zepeda and T. Boubekeur:
Proxy Clouds for Live RGB-D Stream Processing and Consolidation
European Conference on Computer Vision (ECCV) 2018       
(h5-index = 137 at time of publication, 31.8% acceptance)

  ECCV 2018, September 8 - 14, Munich, Germany  

  A. Kaiser, J.A. Ybanez Zepeda and T. Boubekeur:
Geometric Proxies for Live RGB-D Stream Enhancement and Consolidation
ArXiv 2020 (extension paper)     

February 2016
September 2016

A Survey of Simple Geometric Primitives Detection Methods for Captured 3D Data

Work done during my PhD at Telecom Paris in collaboration with Ayotle SAS.
Collaborators: Prof. Tamy Boubekeur, Dr. Jose Alonso Ybanez Zepeda

Keywords: 3D data, 3D geometric primitives, Shape analysis, Shape abstraction, Geometric modeling, Data fitting

The amount of captured 3D data is continuously increasing, with the democratization of consumer depth cameras, the development of modern multi-view stereo capture setups and the rise of single-view 3D capture based on machine learning. The analysis and representation of this ever growing volume of 3D data, often corrupted with acquisition noise and reconstruction artifacts, is a serious challenge at the frontier between computer graphics and computer vision. To that end, segmentation and optimization are crucial analysis components of the shape abstraction process, which can themselves be greatly simplified when performed on lightened geometric formats. In this survey, we review the algorithms which extract simple geometric primitives from raw dense 3D data. After giving an introduction to these techniques, from the acquisition modality to the underlying theoretical concepts, we propose an application-oriented characterization, designed to help select an appropriate method based on one's application needs, and compare recent approaches. We conclude by giving hints for how to evaluate these methods and a set of research challenges to be explored.

  A. Kaiser, J.A. Ybanez Zepeda and T. Boubekeur:
A Survey of Simple Geometric Primitives Detection Methods for Captured 3D Data
Computer Graphics Forum, 38(1):167-196, February 2019 (first published July 2018).     
(h5-index = 49 at time of publication)

  EUROGRAPHICS 2019, May 6-10, Genova, Italy  

February 2014
October 2014

Robust 3D Object Detection and Tracking on Mobile Devices

 

Master's Thesis. Work done while at Wikitude GmbH in collaboration with TU Wien.
Collaborators: Nicolas Goell, Markus Eder

Keywords: Augmented reality, Mobile devices, Scene tracking, Simultaneous Localization And Mapping (SLAM), RGB images, Point features, Edge features, Keyframes, SIMD on embedded CPU (ARM NEON).

Creation of a visual detection and tracking system based on Simultaneous Localization and Mapping (SLAM) for three dimensional objects on mobile devices, for augmented reality applications. Study of the state of the art and implementation of the detector in C++, inspired by existing methods.

July 2012
June 2013

DTIAtlasBuilder

 

Work done as an intern at the NIRAL within the University of North Carolina at Chapel Hill.
Collaborators: Dr. Martin Styner, Francois Budin

Keywords: Brain imaging, Diffusion Tensor Images (DTI), Magnetic Resonance Imaging (MRI), Tractography, 3D voxel registration, Qt, ITK, Graphical user interface, Cross-platform, 3DSlicer.

Development of a user interface for the creation of an atlas image of Diffusion Tensor Images. Cross-platform implementation of the interface in C++ and Python with Qt and ITK to execute the image processing pipeline. Integration to 3DSlicer as an extension.
Several contributions to open-source projects.

  A. R. Verde, F. Budin, J.B. Berger, A. Gupta, M. Farzinfar, A. Kaiser, M. Ahn, H. Johnson, J. Matsui, H. C. Hazlett, A. Sharma, C. Goodlett, Y. Shi, S. Gouttard, C. Vachet, J. Piven, H. Zhu, G. Gerig and M. Styner: UNC-Utah NA-MIC framework for DTI fiber tract analysis
Frontiers in Neuroinformatics, January 2014  
(h5-index = 26 at time of publication)

  2013 NA-MIC All Hands Meeting, Jan 7-11, Salt Lake City, UT, USA  

Student Project Supervision

May 2018
June 2018
IGR205: 4th year Project Seminar of the IGR track at Telecom Paris
Subject: Deep neural network experimentations for geometric primitives detection in RGB-D images
July 2017
Dec 2017
Internship of a 4th year student from Supelec engineering school
Subject: Integration, implementation and optimization of computer vision algorithms
on embedded platform under real-time constraints for 3D scene repositioning
May 2016
Jan 2017
PFEE: Final-year project of the CSAC track at EPITA engineering school
Subject: 3D point cloud scene modeling with a single color camera on mobile devices
May 2016
June 2016
IGR205: 4th year Project Seminar of the IGR track at Telecom Paris
Subject: Fitting geometric primitives to 3D data: implementation and evaluation

Contact

You can contact me at : (first name lowercase) (at sign) (this website)
or via private messages on or .
Last update: 2020/12/17