Learning Implicit Fields for Generative Shape Modeling

By Zhiqin Chen, Hao Zhang. 2018

1,852 citations recorded by the source corpus.

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.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, Generative Models, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

  1. Andreas Geiger
  2. Jonathan T. Barron
  3. Michael Niemeyer
  4. Ben Mildenhall
  5. Pratul P. Srinivasan
  6. Matthew Tancik
  7. Justin Johnson
  8. Matthias Nießner

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Jitendra Malik
  3. Ming-Hsuan Yang
  4. Dacheng Tao
  5. Trevor Darrell
  6. Andrea Vedaldi
  7. Xiaogang Wang
  8. Andreas Geiger

In Generative Models

  1. Andreas Geiger
  2. Jun-Yan Zhu
  3. Richard Zhang
  4. Eli Shechtman
  5. Daniel Cohen-Or
  6. Ming-Hsuan Yang
  7. Alexei A. Efros
  8. Arash Vahdat

In 3D Vision & Pose

  1. Andreas Geiger
  2. Michael Niemeyer
  3. Jitendra Malik
  4. Gerard Pons-Moll
  5. Justin Johnson
  6. Jonathan T. Barron
  7. Angjoo Kanazawa
  8. Songyou Peng

Citations in the corpus