A Non-Linear Differentiable CNN-Rendering Module for 3D Data Enhancement

Yonatan Svirsky, Andrei Sharf

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


In this article we introduce a differentiable rendering module which allows neural networks to efficiently process 3D data. The module is composed of continuous piecewise differentiable functions defined as a sensor array of cells embedded in 3D space. Our module is learnable and can be easily integrated into neural networks allowing to optimize data rendering towards specific learning tasks using gradient based methods in an end-to-end fashion. Essentially, the module's sensor cells are allowed to transform independently and locally focus and sense different parts of the 3D data. Thus, through their optimization process, cells learn to focus on important parts of the data, bypassing occlusions, clutter, and noise. Since sensor cells originally lie on a grid, this equals to a highly non-linear rendering of the scene into a 2D image. Our module performs especially well in presence of clutter and occlusions as well as dealing with non-linear deformations to improve classification accuracy through proper rendering of the data. In our experiments, we apply our module in various learning tasks and demonstrate that using our rendering module we accomplish efficient classification, localization, and segmentation tasks on 2D/3D cluttered and non-cluttered data.

Original languageEnglish
Article number8966278
Pages (from-to)3238-3249
Number of pages12
JournalIEEE Transactions on Visualization and Computer Graphics
Issue number7
StatePublished - 1 Jul 2021


  • Three-dimensional displays
  • Rendering (computer graphics)
  • Shape
  • Task analysis
  • Two dimensional displays
  • Clutter
  • Neural networks
  • 3D convolutional neural networks
  • shape modeling
  • noise removal

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'A Non-Linear Differentiable CNN-Rendering Module for 3D Data Enhancement'. Together they form a unique fingerprint.

Cite this