Image compression optimized for 3D reconstruction by utilizing deep neural networks

Alex Golts, Yoav Y. Schechner

Research output: Contribution to journalArticlepeer-review


Computer vision tasks are often expected to be executed on compressed images. Classical image compression standards like JPEG 2000 are widely used. However, they do not account for the specific end-task at hand. Motivated by works on recurrent neural network (RNN)-based image compression and three-dimensional (3D) reconstruction, we propose unified network architectures to solve both tasks jointly. These joint models provide image compression tailored for the specific task of 3D reconstruction. Images compressed by our proposed models, yield 3D reconstruction performance superior as compared to using JPEG 2000 compression. Our models significantly extend the range of compression rates for which 3D reconstruction is possible. We also show that this can be done highly efficiently at almost no additional cost to obtain compression on top of the computation already required for performing the 3D reconstruction task.

Original languageEnglish
Article number103208
JournalJournal of Visual Communication and Image Representation
StatePublished - Aug 2021


  • 3D reconstruction
  • Deep learning
  • Image compression
  • Recurrent neural networks

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Media Technology
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering


Dive into the research topics of 'Image compression optimized for 3D reconstruction by utilizing deep neural networks'. Together they form a unique fingerprint.

Cite this