Neural Network Assisted Depth Map Packing for Compression Using Standard Hardware Video Codecs

Matti Siekkinen, Teemu Kämäräinen

Research output: Contribution to journalArticleScientificpeer-review

13 Downloads (Pure)


Depth maps are needed by various graphics rendering and processing operations. Depth map streaming is often necessary when such operations are performed in a distributed system and it requires in most cases fast performing compression, which is why video codecs are often used. Hardware implementations of standard video codecs enable relatively high resolution and frame rate combinations, even on resource constrained devices, but unfortunately those implementations do not currently support RGB+depth extensions. However, they can be used for depth compression by first packing the depth maps into RGB or YUV frames. We investigate depth map compression using a combination of depth map packing followed by encoding with a standard video codec. We show that the precision at which depth maps are packed has a large and nontrivial impact on the resulting error caused by the combination of the packing scheme and lossy compression when the bitrate is constrained. Consequently, we propose a variable precision packing scheme assisted by a neural network model that predicts the optimal precision for each depth map given a bitrate constraint. We demonstrate that the model yields near optimal predictions and that it can be integrated into a game engine with very low overhead using modern hardware.

Original languageEnglish
Article number174
Pages (from-to)1-20
Number of pages20
JournalACM Transactions on Multimedia Computing, Communications and Applications
Issue number5s
Publication statusPublished - 7 Jun 2023
MoE publication typeA1 Journal article-refereed


  • Depth map
  • game engine
  • neural network
  • video encoding


Dive into the research topics of 'Neural Network Assisted Depth Map Packing for Compression Using Standard Hardware Video Codecs'. Together they form a unique fingerprint.

Cite this