| Description (include details on usage, files and paper references) | This ETHZ CVL RueMonge 2014 dataset used for 3D reconstruction and semantic mesh labelling for urban scene understanding.
It was first published in [1] and please cite[1] if you use any of its data or source code.
[1] Learning Where To Classify In Multi-View Semantic Segmentation, H. Riemenschneider, A. Bodis-Szomoru, J. Weissenberg, L. Van Gool, ECCV 2014
The dataset comes with the following data:
2D images for training and testing, labelled in 8 classes
3D mesh (faces, vertices) as a 3D representation
Index files for faces to pixels in each image
Training / testing splits as txt files
Sample files for classification results
Sample source code for loading and evaluation (see below)
This sample source code allows the following functions
Evaluate 2D/3D labeling results by (classwise or PASCAL IOU) accuracy.
Examples for loading 2D image data into the 3D mesh (color, labels, probabilities)
Fusion of multiview data by the SUMALL principle (see paper)
Mesh labelling optimization via a graphcut approach.
Various helper tools
This dataset allows the evaluation of semantic classification methods in the following tasks:
TASK 1 - Image Labelling - vanilla 2d img labelling task
TASK 2 - Mesh Labelling - collect or reason in 3d to label mesh
TASK 3 - Pointcloud Labelling - collect or reason in 3d to label point cloud / mesh
TASK 4 - View selection - reason which images to skip for features & classification via view reduction (ECCV paper)
TASK 5 - Scene Coverage - reason which images to skip for features & classification via scene coverage (ECCV paper)
The protocol for training / testing is:
2D Training images are 113 files in 2D (see above: north side)
2D Testing images are the 119 (labelled) images (south side) (on pixel level)
3D Training images are 113 files (see above: north side)
3D Testing images are 119 (labelled) and 202 RGB images (south side) (on mesh face)
http://varcity.eu/3dchallenge/
|
|