The DCM dataset is composed of 772 annotated images from 27 golden age comic books. We freely collected them from the free public domain collection of digitized comic books Digital Comics Museum. One album per available publisher was selected to get as many different styles as possible. We made ground-truth bounding boxes of all panels, all characters (body + faces), small or big, human-like or animal-like.
Image source: https://gitlab.univ-lr.fr/crigau02/dcm-dataset/-/tree/master
Variants: DCM
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Face Detection | DASS-Detector (YOLOX XL) | Domain-Adaptive Self-Supervised Pre-Training for Face … | 2022-11-19 |
| Face Detection | DASS-Detector (YOLOX Tiny) | Domain-Adaptive Self-Supervised Pre-Training for Face … | 2022-11-19 |
| Depth Estimation | Bhattacharjee et al. | Estimating Image Depth in the … | 2021-10-07 |
| Depth Estimation | MIDAS | Towards Robust Monocular Depth Estimation: … | 2019-07-02 |
| Depth Estimation | T2Net | T2Net: Synthetic-to-Realistic Translation for Solving … | 2018-08-04 |
Recent papers with results on this dataset: