Maxime Daisy - Lecturer (ATER)

What's new ?

I am now a PhD

I defended my thesis the 2 of december. Now I am an assistant professor at GREYC laboratory and IUT Cherbourg-Manche, site of Saint-Lô.

Random publication

[ 6 ]  Pierre Buyssens*, Maxime Daisy*, David Tschumperlé, Olivier Lézoray,
Exemplar-based Inpainting : Technical Review and New Heuristics for Better Geometric Reconstructions , IEEE Transactions on Image Processing (TIP) , Vol. 26, n° 6, pp. 1809-1824, 2015
Maxime Daisy
26 years old
Assistant Professor


2012 - 2015
PhD at GREYC Image Team, Caen, FRANCE
Pattern-based image and video inpainting applied to stereoscopic data with depth maps
The funds of this thesis were given to the Action 3DS french national project on stereoscopic systems.
I defended the 2nd december with great honors in front of the following jury:
Yann Gousseau University professor, Télécom ParisTech, Paris, FRANCE Opponent
Patrick Pérez Research director, INRIA and Technicolor, Rennes, FRANCE Opponent
Christine Guillemot Research director, INRIA, Rennes, FRANCE Examiner
Olivier Lézoray University professor, GREYC, Caen, FRANCE Supervisor
David Tschumperlé CNRS research fellow, GREYC, Caen, FRANCE Co-supervisor
2011 - 2012
M. Sc. in Computer Science, in parallel with engineer diploma, University of Caen Normandy
2008 - 2012
Engineer school in computer science, speciality in image & multimedia, ENSI Caen
2006 - 2008
DUT (two-year technical degree) in Communication and Network Services (now multimedia & internet),
IUT Cherbourg-Manche, University of Caen Normandy

Professional experience

2015 - 2016
Assistant professor (ATER), GREYC / IUT Cherbourg-Manche site of Saint-Lô, FRANCE
My students follow a two-year technical degree in multimedia and internet.
Students Subject hours
(two-year technical degree)
Algorithmic & programming 24
Algorithmic & web development 45
Web integration 30
Scientific knowledge & information processing 22.5
Web development 19.5
Object and event oriented programming 30
(engineer degree)
Student project supervision 6
2012 - 2015
Teaching assistant during my PhD, I gave the following courses:
PhD year Students Subject hours
3rd year ENSICAEN
(engineer degree)
C++ programming 51
Introduction to image processing 15
Student project supervision 6
2nd year Bachelor in computer science Methodology 12
Computer science & internet 48
Internship supervision and evaluation 4
1st year DUT
(two-year technical degree)
XML 21
Javascript 43.5
Research internship, master thesis: "Inpainting of synthesised virtual stereo views", GREYC, Caen
Internship: retro-engineering of an inventory database, UBP, Geneve, Switzerland
Internship as webmaster, ERSAM, Caen

Talks / Invited talks

Seminar at Télécom ParisTech
  • GRETSI french national conference
  • CAIP conference
Seminar at GREYC, Caen
  • CORESA french national conference
  • GRETSI french national conference
  • CAIP conference

Skills & Knowledge

Image processing

  • inpainting
  • textures
  • image and video analysis
  • stereoscopy
  • algorithmic of the image processing
  • pattern recognition
  • denoising
  • segmentation

Programming languages

  • C, C++
  • Java
  • PHP, Ruby
  • Javascript


Pierre Buyssens <>
Olivier Lézoray <>
David Tschumperlé <>


French mother tongue
English good level (TOEIC score: 795)
Spanish basic level

Software integration

  • Integration of our inpainting algorithm
    into G'MIC plugin for GIMP

Personal information

  • Driving license
  • Computer assisted music

PhD Thesis

"Pattern-based image and video inpainting applied to stereoscopic data with depth maps"
We focus on the study and the enhancement of greedy pattern-based image processing algorithms for the specific purpose of inpainting, i.e., the automatic completion of missing data in digital images and videos. We first review the state of the art methods in this field and analyze the important steps of prominent greedy algorithms in the literature. Then, we propose a set of changes that significantly enhance the global geometric coherence of images reconstructed with this kind of algorithms. We also focus on the reduction of the visual bloc artifacts classically appearing in the reconstruction results. For this purpose, we define a tensor-inspired formalism for fast anisotropic patch blending, guided by the geometry of the local image structures and by the automatic detection of the artifact locations. We illustrate the improvement of the visual quality brought by our contributions with many examples, and show that we are generic enough to perform similar adaptations to other existing pattern-based inpainting algorithms. Finally, we extend and apply our reconstruction algorithms to stereoscopic image and video data, synthesized with respect to new virtual camera viewpoints. We incorporate the estimated depth information (available from the original stereo pairs) in our inpainting and patch blending formalisms to propose a visually satisfactory solution to the non-trivial problem of automatic disocclusion of real resynthesized stereoscopic scenes.