Projects funded by the NCN

Information on the principal investigator and host institution

Information of the project and the call

Keywords

Equipment

Delete all

Deep generative models for 3D representations

2020/37/B/ST6/03463

Keywords:

generative models deep learning GAN 3D representation binary embeddings point clouds

Descriptors:

  • ST6_011:

Panel:

ST6 - Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems

Host institution :

Politechnika Wrocławska

woj. dolnośląskie

Other projects carried out by the institution 

Principal investigator (from the host institution):

dr Maciej Mateusz Zięba 

Number of co-investigators in the project: 3

Call: OPUS 19 - announced on 2020-03-16

Amount awarded: 652 800 PLN

Project start date (Y-m-d): 2021-02-01

Project end date (Y-m-d): 2024-07-31

Project duration:: 42 months (the same as in the proposal)

Project status: Project settled

Project description

Download the project description in a pdf file

Note - project descriptions were prepared by the authors of the applications themselves and placed in the system in an unchanged form.

Information in the final report

  • Publication in academic press/journals (3)
  • Articles in post-conference publications (5)
  1. The general framework for few-shot learning by kernel HyperNetworks
    Authors:
    Marcin Sendera, Marcin Przewięźlikowski, Jan Miksa, Mateusz Rajski, Konrad Karanowski, Maciej M. Zięba, Jacek Tabor, Przemysław Spurek
    Academic press:
    Machine Vision and Applications (tom: vol. 34, strony: ), Wydawca: Springer
    Status:
    Published
    DOI:
    10.1007/s00138-023-01403-4 - link to the publication
  2. General hypernetwork framework for creating 3D point clouds
    Authors:
    Przemysław Spurek, Maciej Zięba, Jacek Tabor, Tomasz Trzciński
    Academic press:
    IEEE Transactions on Pattern Analysis and Machine Intelligence (tom: vol. 44, nr 12, strony: 9995-10008), Wydawca: IEEE
    Status:
    Published
    DOI:
    TPAMI.2021.3131131 - link to the publication
  3. Continual learning on 3D point clouds with random compressed rehearsal
    Authors:
    Maciej Zamorski, Michał Stypułkowski, Konrad Karanowski, Tomasz Trzciński, Maciej M. Zięba
    Status:
    Accepted for publication
  1. Flow Plugin Network for conditional generation
    Authors:
    Patryk E. Wielopolski, Michał Koperski, Maciej M. Zięba
    Conference:
    Lecture Notes in Computer Science. Lecture Notes in Artificial Intelligence (tom: Intelligent Information and Database Systems 15th Asian Conference, ACIIDS 2023 : Phuket, Thailand, strony: 221-232), Wydawca: Springer
    Data:
    konferencja 24-26.07.2023
    Status:
    Published
    DOI:
    10.1007/978-981-99-5837-5_19 - link to the publication
  2. Eigenvector Grouping for Point Cloud Vessel Labeling
    Authors:
    Patryk Rygiel, Maciej Zieba, Tomasz Konopczynski
    Conference:
    Proceedings of Machine Learning Research 194:72–84, 2022 (tom: GeoMedIA Workshop 2022, strony: 72-84), Wydawca: Proceedings of Machine Learning Research
    Data:
    konferencja 18 listopada
    Status:
    Published
    DOI:
    link to the publication
  3. HyperShot: Few-Shot Learning by Kernel HyperNetworks
    Authors:
    Marcin Sendera, Marcin Przewięźlikowski, Konrad Karanowski, Maciej Zięba, Jacek Tabor, Przemysław Spurek
    Conference:
    2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (tom: Winter Conference on Applications of Computer Vision (WACV), strony: 2468-2477), Wydawca: IEEE
    Data:
    konferencja 3-7.01.2023
    Status:
    Published
  4. Non-Gaussian Gaussian Processes for Few-Shot Regression
    Authors:
    Sendera, Marcin, Jacek Tabor, Aleksandra Nowak, Andrzej Bedychaj, Massimiliano Patacchiola, Tomasz Trzcinski, Przemysław Spurek, and Maciej Zieba
    Conference:
    Advances in Neural Information Processing Systems : 35th Conference on Neural Information Processing Systems (tom: NeurIPS 2021, strony: )
    Status:
    Published
    DOI:
    link to the publication
  5. PluGeN: Multi-Label Conditional Generation From Pre-Trained Models
    Authors:
    Wołczyk, Maciej, Magdalena Proszewska, Łukasz Maziarka, Maciej Zięba, Patryk Wielopolski, Rafał Kurczab, and Marek Śmieja
    Conference:
    Status:
    Accepted for publication

O Narodowym Centrum Nauki

Finansowanie nauki

Współpraca zagraniczna

Centrum prasowe

Deklaracja dostępności
Przetwarzanie danych osobowych
Polityka cookies

Partnerzy