Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation
| Autor: | Marie-Julie Rakotosaona, Maks Ovsjanikov |
|---|---|
| Přispěvatelé: | Laboratoire d'informatique de l'École polytechnique [Palaiseau] (LIX), Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X), Institut Polytechnique de Paris (IP Paris), Lino, Christophe |
| Rok vydání: | 2020 |
| Předmět: |
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]
FOS: Computer and information sciences Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition [INFO.INFO-GR] Computer Science [cs]/Graphics [cs.GR] Point cloud 02 engineering and technology Regularization (mathematics) [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] Computer Science - Graphics Encoding (memory) 0202 electrical engineering electronic engineering information engineering Code (cryptography) [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC] [INFO.INFO-MM] Computer Science [cs]/Multimedia [cs.MM] business.industry Deep learning 3D reconstruction [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM] 020207 software engineering [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR] Graphics (cs.GR) Dual (category theory) 020201 artificial intelligence & image processing Artificial intelligence [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC] business Algorithm Interpolation |
| Zdroj: | Lecture Notes in Computer Science Lecture Notes in Computer Science-Computer Vision – ECCV 2020 Computer Vision – ECCV 2020-16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II Computer Vision – ECCV 2020 ISBN: 9783030585358 ECCV (2) |
| ISSN: | 0302-9743 1611-3349 |
| DOI: | 10.48550/arxiv.2004.01661 |
| Popis: | We present a learning-based method for interpolating and manipulating 3D shapes represented as point clouds, that is explicitly designed to preserve intrinsic shape properties. Our approach is based on constructing a dual encoding space that enables shape synthesis and, at the same time, provides links to the intrinsic shape information, which is typically not available on point cloud data. Our method works in a single pass and avoids expensive optimization, employed by existing techniques. Furthermore, the strong regularization provided by our dual latent space approach also helps to improve shape recovery in challenging settings from noisy point clouds across different datasets. Extensive experiments show that our method results in more realistic and smoother interpolations compared to baselines. Both the code and our pre-trained network can be found online: https://github.com/mrakotosaon/intrinsic_interpolations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|