Timezone: »

UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree
Kacper Kania · Maciej Zieba · Tomasz Kajdanowicz

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #1119

Signed distance field (SDF) is a prominent implicit representation of 3D meshes. Methods that are based on such representation achieved state-of-the-art 3D shape reconstruction quality. However, these methods struggle to reconstruct non-convex shapes. One remedy is to incorporate a constructive solid geometry framework (CSG) that represents a shape as a decomposition into primitives. It allows to embody a 3D shape of high complexity and non-convexity with a simple tree representation of Boolean operations. Nevertheless, existing approaches are supervised and require the entire CSG parse tree that is given upfront during the training process. On the contrary, we propose a model that extracts a CSG parse tree without any supervision - UCSG-Net. Our model predicts parameters of primitives and binarizes their SDF representation through differentiable indicator function. It is achieved jointly with discovering the structure of a Boolean operators tree. The model selects dynamically which operator combination over primitives leads to the reconstruction of high fidelity. We evaluate our method on 2D and 3D autoencoding tasks. We show that the predicted parse tree representation is interpretable and can be used in CAD software.

Author Information

Kacper Kania (Wrocław University of Science and Technology)
Maciej Zieba (Wroclaw University of Science and Technology, Tooploox)
Tomasz Kajdanowicz (Wroclaw University of Science and Technology, Wyb. Wyspianskiego 27, PL8960005851)

More from the Same Authors

  • 2022 : Neural Architecture for Online Ensemble Continual Learning »
    Mateusz Wójcik · Witold Kościukiewicz · Adam Gonczarek · Tomasz Kajdanowicz
  • 2022 Poster: FlowHMM: Flow-based continuous hidden Markov models »
    Pawel Lorek · Rafal Nowak · Tomasz Trzcinski · Maciej Zieba
  • 2022 Poster: This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish »
    Lukasz Augustyniak · Kamil Tagowski · Albert Sawczyn · Denis Janiak · Roman Bartusiak · Adrian Szymczak · Arkadiusz Janz · Piotr Szymański · Marcin Wątroba · Mikołaj Morzy · Tomasz Kajdanowicz · Maciej Piasecki
  • 2021 Poster: Non-Gaussian Gaussian Processes for Few-Shot Regression »
    Marcin Sendera · Jacek Tabor · Aleksandra Nowak · Andrzej Bedychaj · Massimiliano Patacchiola · Tomasz Trzcinski · Przemysław Spurek · Maciej Zieba
  • 2019 : Coffee Break & Poster Session 1 »
    Yan Zhang · Jonathon Hare · Adam Prugel-Bennett · Po Leung · Patrick Flaherty · Pitchaya Wiratchotisatian · Alessandro Epasto · Silvio Lattanzi · Sergei Vassilvitskii · Morteza Zadimoghaddam · Theja Tulabandhula · Fabian Fuchs · Adam Kosiorek · Ingmar Posner · William Hang · Anna Goldie · Sujith Ravi · Azalia Mirhoseini · Yuwen Xiong · Mengye Ren · Renjie Liao · Raquel Urtasun · Haici Zhang · Michele Borassi · Shengda Luo · Andrew Trapp · Geoffroy Dubourg-Felonneau · Yasmeen Kussad · Christopher Bender · Manzil Zaheer · Junier Oliva · Michał Stypułkowski · Maciej Zieba · Austin Dill · Chun-Liang Li · Songwei Ge · Eunsu Kang · Oiwi Parker Jones · Kelvin Ka Wing Wong · Joshua Payne · Yang Li · Azade Nazi · Erkut Erdem · Aykut Erdem · Kevin O'Connor · Juan J Garcia · Maciej Zamorski · Jan Chorowski · Deeksha Sinha · Harry Clifford · John W Cassidy
  • 2018 Poster: BinGAN: Learning Compact Binary Descriptors with a Regularized GAN »
    Maciej Zieba · Piotr Semberecki · Tarek El-Gaaly · Tomasz Trzcinski