Learning Implicit Fields for Generative Shape Modeling
arXiv:1812.02822
Abstract
We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder, called IM-NET, for shape generation, aimed at improving the visual quality of the generated shapes. An implicit field assigns a value to each point in 3D space, so that a shape can be extracted as an iso-surface. IM-NET is trained to perform this assignment by means of a binary classifier. Specifically, it takes a point coordinate, along with a feature vector encoding a shape, and outputs a value which indicates whether the point is outside the shape or not. By replacing conventional decoders by our implicit decoder for representation learning (via IM-AE) and shape generation (via IM-GAN), we demonstrate superior results for tasks such as generative shape modeling, interpolation, and single-view 3D reconstruction, particularly in terms of visual quality. Code and supplementary material are available at https://github.com/czq142857/implicit-decoder.
arXiv commentAccepted to CVPR 2019. Code: https://github.com/czq142857/implicit-decoder Project page: https://www.sfu.ca/~zhiqinc/imgan/Readme.html
References in corpus (7)
- Auto-Encoding Variational Bayes
- Conditional Image Generation with PixelCNN Decoders
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
- Learning Representations and Generative Models for 3D Point Clouds
- Deep Generative Stochastic Networks Trainable by Backprop
- Better Mixing via Deep Representations
- Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction
Cited by in corpus (7)
- DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction
- CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis
- Controlling Neural Level Sets
- Fast Neural Representations for Direct Volume Rendering
- UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree
- IntraSeismic: a coordinate-based learning approach to seismic inversion
- ImpliCity: City Modeling from Satellite Images with Deep Implicit Occupancy Fields