PROX datasets

by Mohamed HassanResearch Only

PROX datasets

We collect a new dataset composed of 12 different 3D scenes and RGB sequences of 20 subjects moving in and interacting with the scenes. Quantitative PROX dataset : Dataset of 180 static RGB-D frames with Ground Truth. The dataset captures static RGB-D frames of 1 subject in 1 scene and is described in Section 4.2 of the PROX paper. Qualitative PROX dataset: Dataset of 100K RGB-D frames pseudo Ground Truth. The dataset captures dynamic RGB-D sequences of 20 subjects in 12 scenes and is described in Section 4.1.2 on the PROX paper.

Dataset Attributes

Label SVG
Tasks3D Pose Estimation
Label SVG
CategoriesHumans, Body, Actions
Label SVG
SensorRGB-D Camera

Class Labels

Body segmentsFittingsKeypoints