Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich

Menu
Home Data Datasets Intrinsic3D

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Last revision Both sides next revision
data:datasets:intrinsic3d [2017/11/28 16:21]
Robert Maier
data:datasets:intrinsic3d [2019/02/28 10:17]
Robert Maier
Line 26: Line 26:
   * Depth frames (frame-XXXXXX.depth.png):​ depth (mm), 16-bit, PNG (invalid depth is set to 0)   * Depth frames (frame-XXXXXX.depth.png):​ depth (mm), 16-bit, PNG (invalid depth is set to 0)
   * Camera poses (frame-XXXXXX.pose.txt):​ camera-to-world pose computed by [[https://​github.com/​niessner/​VoxelHashing|VoxelHashing]]   * Camera poses (frame-XXXXXX.pose.txt):​ camera-to-world pose computed by [[https://​github.com/​niessner/​VoxelHashing|VoxelHashing]]
-  * Camera calibration (colorIntrinsics.txt and depthIntrinsics.txt): ​the color and depth camera intrinsics (default factory calibration). ​+  * Camera calibration (colorIntrinsics.txt and depthIntrinsics.txt):​ color and depth camera intrinsics (default factory calibration). ​
  
-For reference, the RGB-D data is provided in the same format as specified [[http://​graphics.stanford.edu/​projects/​vsfs/​|here]].+For reference, the RGB-D data is provided in the same format as specified [[http://​graphics.stanford.edu/​projects/​vsfs/​|here]]. The [[https://​github.com/​NVlabs/​intrinsic3d|Intrinsic3D source code on github]] can directly read and process sequences in this format.
  
 ==== Lion ==== ==== Lion ====

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching

info@vision.in.tum.de