Recent Releases of https://github.com/cuiziteng/eccv_raw_adapter
https://github.com/cuiziteng/eccv_raw_adapter - PASCAL RAW dataset results
Object Detection on PASCAL RAW dataset.
PASCAL RAW: Download PASCAL RAW dataset from Google Drive or 百度网盘 (passwd: oiab)
Which format as:
``` -- data -- PASCALRAWgithub -- annotations -- original (original RAW, demosaic RAW normal-light & over-exposure & low-light) -- compare_ISP (ISP methods, InvISP, ECCV16-ISP) -- trainval
```
- Jupyter Notebook
Published by cuiziteng over 1 year ago
https://github.com/cuiziteng/eccv_raw_adapter - LOD dataset Results
Object Detection on LOD dataset.
LOD: Download LOD dataset from Google Drive or 百度网盘 (passwd: kf43), or find the LOD dataset original provide link.
Which format as:
-- data
-- LOD_BMVC21
-- RAW_dark (RAW data, "demosacing" in our paper)
-- RGB_dark (default ISP RGB data)
-- RAW_dark_InverseISP (InvISP processed RAW data, [CVPR 2021])
-- RAW_dark_ECCV16_Micheal (ECCV16 ISP processed RAW data, [ECCV 2016])
-- RAW-dark-Annotations (detection label)
-- trainval
- Jupyter Notebook
Published by cuiziteng over 1 year ago
https://github.com/cuiziteng/eccv_raw_adapter -
ADE 20K RAW Segmentation weights:
RAW-Adapters (SegFormer with MIT-B5/B3/B1 backbone) : normal-light & over-exposure & low-light
Demosaic (SegFormer with MIT-B5 backbone) : normal-light & over-exposure & low-light
Other Compare Methods (SegFormer with MIT-B5 backbone):
InvISP: normal-light & over-exposure & low-light ECCV 16 ISP: normal-light & over-exposure & low-light SID: low-light
- Jupyter Notebook
Published by cuiziteng over 1 year ago