GraphX-Convolution for Point Cloud Deformation in 2D-to-3D Conversion
| Autor: | Seonghwa Choi, Duc Nguyen, Sanghoon Lee, Woojae Kim |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computational Geometry (cs.CG)
FOS: Computer and information sciences Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) Feature extraction Computer Science - Computer Vision and Pattern Recognition Point cloud ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Solid modeling 010501 environmental sciences 01 natural sciences Convolution Machine Learning (cs.LG) 0202 electrical engineering electronic engineering information engineering 0105 earth and related environmental sciences business.industry 3D reconstruction 2D to 3D conversion 020206 networking & telecommunications Computer Science - Computational Geometry Graph (abstract data type) Artificial intelligence business Algorithm |
| Zdroj: | ICCV |
| DOI: | 10.48550/arxiv.1911.06600 |
| Popis: | In this paper, we present a novel deep method to reconstruct a point cloud of an object from a single still image. Prior arts in the field struggle to reconstruct an accurate and scalable 3D model due to either the inefficient and expensive 3D representations, the dependency between the output and number of model parameters or the lack of a suitable computing operation. We propose to overcome these by deforming a random point cloud to the object shape through two steps: feature blending and deformation. In the first step, the global and point-specific shape features extracted from a 2D object image are blended with the encoded feature of a randomly generated point cloud, and then this mixture is sent to the deformation step to produce the final representative point set of the object. In the deformation process, we introduce a new layer termed as GraphX that considers the inter-relationship between points like common graph convolutions but operates on unordered sets. Moreover, with a simple trick, the proposed model can generate an arbitrary-sized point cloud, which is the first deep method to do so. Extensive experiments verify that we outperform existing models and halve the state-of-the-art distance score in single image 3D reconstruction. Comment: In Proceedings of the IEEE International Conference on Computer Vision 2019. Fixed minor details and added some updates. Project page: https://git.io/JeovA |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|