Maciej Zamorski

Maciej Zamorski

Auto-generated profile, based on publicly available information

Maciej Zamorski

Wrocław University of Science and Technology

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2020 in Computer Vision and Image Understanding
Verified
Journal Article
Closed access
MZMaciej Zamorski
Maciej Zamorski
MZMaciej Zięba
Maciej Zięba
PKPiotr Klukowski
Piotr Klukowski
RNRafał Nowak
Rafał Nowak
KKKarol Kurach
Karol Kurach
TTTomasz Trzciński
Tomasz Trzciński

5 January 2023 in Computer Vision and Image Understanding
Verified
Journal Article
Closed access
MZMaciej Zamorski
Maciej Zamorski
MSMichał Stypułkowski
Michał Stypułkowski
KKKonrad Karanowski
Konrad Karanowski
TTTomasz Trzciński
Tomasz Trzciński
MZMaciej Zięba
Maciej Zięba

24 May 2019
Verified
Book Chapter
Closed access
PDF file
MZMaciej Zamorski
Maciej Zamorski
AZAdrian Zdobylak
Adrian Zdobylak
MZMaciej Zięba
Maciej Zięba
JŚJerzy Świątek
Jerzy Świątek

7 March 2019
Verified
Book Chapter
Closed access
PDF file
MZMaciej Zamorski
Maciej Zamorski
MZMaciej Zięba
Maciej Zięba

18 May 2018 in Journal of Biomolecular NMR
Verified
Journal Article
Closed access
PDF file
PKPiotr Klukowski
Piotr Klukowski
MAMichał Augoff
Michał Augoff
MZMaciej Zamorski
Maciej Zamorski
AGAdam Gonczarek
Adam Gonczarek
MWMichał J. Walczak
Michał J. Walczak

1 May 2019 in arXiv
Verified
Preprint
Open access
PDF file
MZMaciej Zamorski
Maciej Zamorski
MZMaciej Zięba
Maciej Zięba
PKPiotr Klukowski
Piotr Klukowski
RNRafał Nowak
Rafał Nowak
KKKarol Kurach
Karol Kurach
TTTomasz Trzciński
Tomasz Trzciński
Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds. In this work, we present a novel method to obtain meaningful representations of 3D shapes that can be used for challenging tasks including 3D points generation, reconstruction, compression, and clustering. Contrary to existing methods for 3D point cloud generation that train separate decoupled models for representation learning and generation, our approach is the first end-to-end solution that allows to simultaneously learn a latent space of representation and generate 3D shape out of it. Moreover, our model is capable of learning meaningful compact binary descriptors with adversarial training conducted on a latent space. To achieve this goal, we extend a deep Adversarial Autoencoder model (AAE) to accept 3D input and create 3D output. Thanks to our end-to-end training regime, the resulting method called 3D Adversarial Autoencoder (3dAAE) obtains either binary or continuous latent space that covers a much wider portion of training data distribution. Finally, our quantitative evaluation shows that 3dAAE provides state-of-the-art results for 3D points clustering and 3D object retrieval.