Institute Homepage DE Sign In

Back

Perceiving Systems Conference Paper 2014

OpenDR: An Approximate Differentiable Renderer

Thumb ticker sm thumb img 1090
Perceiving Systems
Matthew Loper
Thumb ticker sm headshot2021
Perceiving Systems
Michael Black
Director
Opendr

Inverse graphics attempts to take sensor data and infer 3D geometry, illumination, materials, and motions such that a graphics renderer could realistically reproduce the observed scene. Renderers, however, are designed to solve the forward process of image synthesis. To go in the other direction, we propose an approximate di fferentiable renderer (DR) that explicitly models the relationship between changes in model parameters and image observations. We describe a publicly available OpenDR framework that makes it easy to express a forward graphics model and then automatically obtain derivatives with respect to the model parameters and to optimize over them. Built on a new autodiff erentiation package and OpenGL, OpenDR provides a local optimization method that can be incorporated into probabilistic programming frameworks. We demonstrate the power and simplicity of programming with OpenDR by using it to solve the problem of estimating human body shape from Kinect depth and RGB data.

Author(s): Matthew M. Loper and Michael J. Black
Book Title: Computer Vision – ECCV 2014
Volume: 8695
Pages: 154--169
Year: 2014
Month: September
Series: Lecture Notes in Computer Science
Editors: D. Fleet and T. Pajdla and B. Schiele and T. Tuytelaars
Publisher: Springer International Publishing
Project(s):
Bibtex Type: Conference Paper (inproceedings)
DOI: 10.1007/978-3-319-10584-0_11
Event Name: 13th European Conference on Computer Vision
Event Place: Zürich, Switzerland
Electronic Archiving: grant_archive
Links:

BibTex 

@inproceedings{Loper:ECCV:2014,
  title = {{OpenDR}: An Approximate Differentiable Renderer},
  booktitle = {Computer Vision -- ECCV 2014},
  abstract = {Inverse graphics attempts to take sensor data and infer 3D geometry, illumination, materials, and motions such that a graphics renderer could realistically reproduce the observed scene. Renderers, however, are designed to solve the forward process of image synthesis. To go in the other direction, we propose an approximate differentiable renderer (DR) that explicitly models the relationship between changes in model parameters and image observations. We describe a publicly available OpenDR framework that makes it easy to express a forward graphics model and then automatically obtain derivatives with respect to the model parameters and to optimize over them. Built on a new autodifferentiation package and OpenGL, OpenDR provides a local optimization method that can be incorporated into probabilistic programming frameworks. We demonstrate the power and simplicity of programming with OpenDR by using it to solve the problem of estimating human body shape from Kinect depth and RGB data.},
  volume = {8695},
  pages = {154--169},
  series = {Lecture Notes in Computer Science},
  editors = {D. Fleet  and T. Pajdla and B. Schiele  and T. Tuytelaars },
  publisher = {Springer International Publishing},
  month = sep,
  year = {2014},
  slug = {loper-eccv-2014},
  author = {Loper, Matthew M. and Black, Michael J.},
  month_numeric = {9}
}