PifPaf: Composite Fields for Human Pose Estimation

CVPR 2019 Sven KreissLorenzo BertoniAlexandre Alahi

We propose a new bottom-up method for multi-person 2D human pose estimation that is particularly well suited for urban mobility such as self-driving cars and delivery robots. The new method, PifPaf, uses a Part Intensity Field (PIF) to localize body parts and a Part Association Field (PAF) to associate body parts with each other to form full human poses... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Keypoint Detection COCO test-dev PifPaf (single-scale) APL 72.1 # 8
APM 62.6 # 8
AP 66.4 # 2