OperatorNet: Recovering 3D Shapes From Difference Operators
| Autor: | Maks Ovsjanikov, Panos Achlioptas, Ruqi Huang, Marie-Julie Rakotosaona, Leonidas J. Guibas |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Context (language use) 02 engineering and technology Iterative reconstruction 010501 environmental sciences 01 natural sciences Matrix (mathematics) Computer Science - Graphics Operator (computer programming) 0202 electrical engineering electronic engineering information engineering 0105 earth and related environmental sciences ComputingMethodologies_COMPUTERGRAPHICS Basis (linear algebra) business.industry Multiplicative function 020207 software engineering Graphics (cs.GR) Embedding Artificial intelligence business Laplace operator Algorithm Interpolation |
| Zdroj: | 2019 IEEE/CVF International Conference on Computer Vision (ICCV) ICCV |
| DOI: | 10.1109/iccv.2019.00868 |
| Popis: | This paper proposes a learning-based framework for reconstructing 3D shapes from functional operators, compactly encoded as small-sized matrices. To this end we introduce a novel neural architecture, called OperatorNet, which takes as input a set of linear operators representing a shape and produces its 3D embedding. We demonstrate that this approach significantly outperforms previous purely geometric methods for the same problem. Furthermore, we introduce a novel functional operator, which encodes the extrinsic or pose-dependent shape information, and thus complements purely intrinsic pose-oblivious operators, such as the classical Laplacian. Coupled with this novel operator, our reconstruction network achieves very high reconstruction accuracy, even in the presence of incomplete information about a shape, given a soft or functional map expressed in a reduced basis. Finally, we demonstrate that the multiplicative functional algebra enjoyed by these operators can be used to synthesize entirely new unseen shapes, in the context of shape interpolation and shape analogy applications. Comment: Accepted to ICCV 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|