AHP (Amodal Human Perception)
Introduced by Zhou et al. in Human De-occlusion: Invisible Perception and Recovery for Humans
The AHP dataset consists of 56,599 images in total which are collected from several large-scale instance segmentation and detection datasets, including COCO, VOC (w/ SBD), LIP, Objects365 and OpenImages. Each image is annotated with a pixel-level segmentation mask of a single integrated human.
The dataset is initially proposed to solve the task of human de-occlusion.
Data Splits
- Train: Totally 56,302 images with annotations of integrated humans.
- Valid: Totally 297 images of synthesized occlusion cases.
- Test: Totally 56 images of artificial occlusion cases.
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
No data loaders found. You can
submit your data loader here.
No data loaders found. You can
submit your data loader here.
