Perzeptive Systeme PS:License 1.0 2021-06-22

AGORA dataset

Thumb ticker sm img 20181018 102914
Perzeptive Systeme
  • Guest Scientist
Thumb ticker sm head
Perzeptive Systeme
  • Guest Scientist
Thumb ticker sm tesch
Perzeptive Systeme
Software Engineer, Real-time Graphics (VR/MR)
Thumb ticker sm bild
Perzeptive Systeme
Thumb ticker sm shashank
Perzeptive Systeme
  • Doctoral Researcher
Thumb ticker sm headshot2021
Perzeptive Systeme
Director
Ezgif.com gif maker

While the accuracy of 3D human pose estimation from images has steadily improved on benchmark datasets, the best methods still fail in many real-world scenarios. This suggests that there is a domain gap between current datasets and common scenes containing people. To evaluate the current state-of-the-art methods on more challenging images, and to drive the field to address new problems, we introduce AGORA, a synthetic dataset with high realism and highly accurate ground truth. We create around 14K training and 3K test images by rendering between 5 and 15 people per image using either image-based lighting or rendered 3D environments, taking care to make the images physically plausible and photoreal. In total, AGORA consists of 173K individual person crops.

Release Date: 22 June 2021
licence_type: PS:License 1.0
Authors: Patel, P., Huang, C. P., Tesch, J., Hoffmann, D. T., Tripathi, S., Black, M. J.
Link (URL): https://agora.is.tue.mpg.de/
Repository: https://github.com/pixelite1201/agora_evaluation