About me

I received my PhD in Computer Vision and Machine Learning from the CY Cergy Paris University (Université de Cergy-Pontoise), France, in April 2019. My thesis was developed at the ETIS Lab under the supervision of David Picard and Hedi Tabia and supported by the Brazilian National Council for Scientific and Technological Development (CNPq). I received my Master's degree in Applied Computing (Graphics and Computer Vision) from the Federal University of Technology - Paraná (UTFPR), Brazil, in 2015, and my Bachelor's degree in Electronics Engineering from the UTFPR, in 2011. I have worked with computer vision applied to embedded and real-time systems (2011-2015), and with computer vision algorithms for on-device applications at Samsung (2019-2021). Since 2021, I am a Postdoctoral Researcher at the Max-Planck-Institut für Informatik, under the supervision of Christian Theobalt, and a Research Member of the Saarbrücken Research Center for Visual Computing, Interaction and Artificial Intelligence (VIA Research Center, a partnership between MPI-INF and Google). See my official web page at MPI-INF for more information.

Research Interests

My research interests are mainly focused on solving complex problems in the areas of Computer Vision, Computer Graphics, and Deep Learning, specially applied to modeling humans in their environment. I am passionate about working on challenging research problems that have a real impact on people's lives.

News

Publications

Please see my Web Page @ MPI-INF and my Google Scholar for recent publications.

Adaptive Multiplane Image Generation from a Single Internet Picture

Diogo C. Luvizon, Gustavo Sutter P. Carvalho, Andreza A. dos Santos, Jhonatas S. Conceicão, Jose L. Flores-Campana, Luis G. L. Decker, Marcos R. Souza, Helio Pedrini, Antonio Joia, Otávio A. B. Penatti. The IEEE Winter Conference on Applications of Computer Vision (WACV), 2021.

[the CVF] [arXiv] [video]

Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation

Allan Pinto, Manuel A. Córdova, Luis G. L. Decker, Jose L. Flores-Campana, Marcos R. Souza, Andreza A. dos Santos, Jhonatas S. Conceição, Henrique F. Gagliardi, Diogo C. Luvizon, Ricardo da S. Torres, and Helio Pedrini. The IEEE International Conference on Image Processing (ICIP), 2020.

[pdf] [project page] [bibtex]

Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition

Diogo Luvizon, David Picard, Hedi Tabia. The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020.

[ieeexplorer] [pdf] [code] [bibtex]

Human pose regression by combining indirect part detection and contextual information

Diogo C. Luvizon, Hedi Tabia, David Picard. Computers & Graphics, 2019.

[pdf] [code] [bibtex]

2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning

Diogo C. Luvizon, David Picard, Hedi Tabia. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

[pdf] [supp] [demo] [code] [bibtex]

Learning features combination for human action recognition from skeleton sequences

Diogo Carbonera Luvizon, Hedi Tabia, David Picard. Pattern Recognition Letters, 2017.

[pdf] [code] [bibtex] [elsevier]

A Video-Based System for Vehicle Speed Measurement in Urban Roadways

Diogo C. Luvizon, Bogdan T. Nassu, Rodrigo Minetto. The IEEE Transactions on Intelligent Transportation Systems (ITS), 2017.

[pdf] [code] [demo] [bibtex] [ieeexplore]

Vehicle speed estimation by license plate detection and tracking

Diogo C. Luvizon, Bogdan T. Nassu, Rodrigo Minetto. The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014.

[bibtex] [ieeexplore]

Patents

- Granted! Diogo Carbonera Luvizon; Henrique Fabricio Gagliardi; Otavio Augusto Bizetto Penatti. "Method for generating an adaptive multiplane image from a single high-resolution image", US 11,704,778 B2, 2023, Samsung.
- Luvizon, Diogo Carbonera; Pessurno De, Carvalho Gustavo Sutter; Bizetto Penatti, Otavio Augusto. "COMPUTER IMPLEMENTED METHOD AND SYSTEM FOR CLASSIFYING AN INPUT IMAGE FOR NEW VIEW SYNTHESIS IN A 3D VISUAL EFFECT, AND NON-TRANSITORY COMPUTER READABLE STORAGE MEDIUM", US 2023/0196659 A1, 2023, Samsung.
- LUVIZON, DIOGO C.; MINETTO, RODRIGO; NASSU, B. T. "Sistema para Medição de Velocidade Instantânea e Média de Veículos por Reconhecimento de Padrões em Imagens e Vídeos Digitais", INPI - Instituto Nacional da Propriedade Industrial, Registro No. BR10201503191, 2015 (Brazil, in Portuguese).

Awards and Prizes

- Best Paper Honorable Mention on the Symposium on Vision, Modeling, and Visualization (GCPR-VMV), 2022, Konstanz, Germany. [Project Page]
- Best Presentation Award in the annual ETIS Lab workshop, 2018, France.
- 1st Prize on Workshop of Theses and Dissertations (WTD - Master), Conference on Graphics, Patterns and Images (SIBGRAPI), 2016, Brazil. Master's Thesis available here.
- 2nd Prize on Concurso Latino-Americano de Dissertações de Mestrado (CLTM), Conferência Latino-Americana de Informática (CLEI), 2016, Chile.
- Individual Grant (90K) from the Brazilian National Council for Scientific and Technological Development (CNPq) for PhD abroad, 2015.

Teaching - Master Sc. (at ENSEA, 2017-2018)

UEC-1-IMD Int. images et multimedia

  • Action recognition from skeletons, VLAD, and LMNN: slides
  • Intro. to Neural Networks and Deep Learning: slides
  • Intro. to Generative Adversarial Networks: slides
  • IA et Big Data: TP GANs 2018-2019 link

Source Code

The public source code related to my work is available on my GitHub.

Contact

  • Address

    Diogo Carbonera Luvizon
    Max-Planck-Institut für Informatik, Saarbrücken, Germany
    Visual Computing and Artificial Intelligence
    VIA Research Center

  • Email

    dluvizon [at] mpi-inf.mpg.de

  • Language

    Fluent in English, French, and Portuguese; basic German