Neural Shape Parsers for Constructive Solid Geometry

Constructive solid geometry (CSG) is a geometric modeling technique that defines complex shapes by recursively applying boolean operations on primitives such as spheres and cylinders. We present CSGNet , a deep network architecture that takes as input a 2D or 3D shape and outputs a CSG program that...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence Jg. 44; H. 5; S. 2628 - 2640
Hauptverfasser: Sharma, Gopal, Goyal, Rishabh, Liu, Difan, Kalogerakis, Evangelos, Maji, Subhransu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.05.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
Annotations
Boolean algebra
Coders
Computer architecture
Constructive solid geometry
Decoding
Grammar
Image Processing, Computer-Assisted - methods
Image reconstruction
Modelling
Neural Networks, Computer
reinforcement learning
Shape
shape parsing
Software
Solid modeling
Task analysis
Three-dimensional displays
Two dimensional displays
Two dimensional models
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Constructive solid geometry (CSG) is a geometric modeling technique that defines complex shapes by recursively applying boolean operations on primitives such as spheres and cylinders. We present CSGNet , a deep network architecture that takes as input a 2D or 3D shape and outputs a CSG program that models it. Parsing shapes into CSG programs is desirable as it yields a compact and interpretable generative model. However, the task is challenging since the space of primitives and their combinations can be prohibitively large. CSGNet uses a convolutional encoder and recurrent decoder based on deep networks to map shapes to modeling instructions in a feed-forward manner and is significantly faster than bottom-up approaches. We investigate two architectures for this task-a vanilla encoder (CNN) - decoder (RNN) and another architecture that augments the encoder with an explicit memory module based on the program execution stack. The stack augmentation improves the reconstruction quality of the generated shape and learning efficiency. Our approach is also more effective as a shape primitive detector compared to a state-of-the-art object detector. Finally, we demonstrate CSGNet can be trained on novel datasets without program annotations through policy gradient techniques.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2020.3044749