TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/Panoptic

Panoptic

CMU Panoptic Studio

ImagesCustom (non-commercial)Introduced 2015-01-01

CMU Panoptic is a large scale dataset providing 3D pose annotations (1.5 millions) for multiple people engaging social activities. It contains 65 videos (5.5 hours) with multi-view annotations, but only 17 of them are in multi-person scenario and have the camera parameters.

Massively Multiview System

  • 480 VGA camera views
  • 30+ HD views
  • 10 RGB-D sensors
  • Hardware-based sync
  • Calibration
  • Interesting Scenes with Labels

Multiple people

  • Socially interacting groups
  • 3D body pose
  • 3D facial landmarks
  • Transcripts + speaker ID

Hardware setup

  • 480 VGA cameras, 640 x 480 resolution, 25 fps, synchronized among themselves using a hardware clock
  • 31 HD cameras, 1920 x 1080 resolution, 30 fps, synchronized among themselves using a hardware clock, timing aligned with VGA cameras
  • 10 Kinect Ⅱ Sensors. 1920 x 1080 (RGB), 512 x 424 (depth), 30 fps, timing aligned among themselves and other sensors 5 DLP Projectors. synchronized with HD cameras

Source: Single-Stage Multi-Person Pose Machines Image Source: http://domedb.perception.cs.cmu.edu/

Benchmarks

1 Image, 2*2 Stitchi/Average MPJPE (mm)1 Image, 2*2 Stitchi/Geodesic Error (GE)3D/Average MPJPE (mm)3D/Geodesic Error (GE)3D Human Pose Estimation/Average MPJPE (mm)3D Human Pose Tracking/3DMOTA3D Multi-Person Pose Estimation/Average MPJPE (mm)Pose Estimation/Average MPJPE (mm)Pose Estimation/Geodesic Error (GE)Pose Tracking/3DMOTA

Related Benchmarks

Panoptic SYNTHIA-to-Cityscapes/Domain Adaptation/mPQPanoptic SYNTHIA-to-Mapillary/Domain Adaptation/mPQPanoptic nuScenes test/10-shot image generation/PQPanoptic nuScenes test/10-shot image generation/RQPanoptic nuScenes test/10-shot image generation/SQPanoptic nuScenes test/10-shot image generation/mIoUPanoptic nuScenes test/Panoptic Segmentation/PQPanoptic nuScenes test/Panoptic Segmentation/RQPanoptic nuScenes test/Panoptic Segmentation/SQPanoptic nuScenes test/Panoptic Segmentation/mIoUPanoptic nuScenes test/Semantic Segmentation/PQPanoptic nuScenes test/Semantic Segmentation/RQPanoptic nuScenes test/Semantic Segmentation/SQPanoptic nuScenes test/Semantic Segmentation/mIoUPanoptic nuScenes val/10-shot image generation/PQPanoptic nuScenes val/10-shot image generation/RQPanoptic nuScenes val/10-shot image generation/SQPanoptic nuScenes val/10-shot image generation/mIoUPanoptic nuScenes val/Panoptic Segmentation/PQPanoptic nuScenes val/Panoptic Segmentation/RQPanoptic nuScenes val/Panoptic Segmentation/SQPanoptic nuScenes val/Panoptic Segmentation/mIoUPanoptic nuScenes val/Semantic Segmentation/PQPanoptic nuScenes val/Semantic Segmentation/RQPanoptic nuScenes val/Semantic Segmentation/SQPanoptic nuScenes val/Semantic Segmentation/mIoU

Statistics

Papers
131
Benchmarks
10

Links

Homepage

Tasks

1 Image, 2*2 Stitchi3D3D Human Pose Estimation3D Human Pose Tracking3D Multi-Person Pose EstimationHead Pose EstimationPose EstimationPose Tracking