PolarAPP checkpoints

This repository contains the released checkpoints for the two downstream tasks in PolarAPP:

• SfP/: full-resolution shape from polarization with a TaskNet designed specifically for PolarAPP.
• DfP/: full-resolution de-reflection from polarization with a PolarFree-based TaskNet.

Files

SfP/
|-- DemNet/DemNet.pth
|-- TaskNet/TaskNet.pth
`-- FANet/FANet.pth

DfP/
|-- DemNet/DemNet.pth
|-- TaskNet/TaskNet.pth
`-- FANet/FANet.pth

DemNet reconstructs full-resolution polarization observations. TaskNet performs the downstream task. FANet supports feature alignment during training.

Download

from huggingface_hub import snapshot_download

checkpoint_root = snapshot_download("Roydon728/PolarAPP")

Pass the task subdirectory to the corresponding inference command:

cd SfP
python infer.py --input-dir ./Datasets/Testsets --ckpt-dir <snapshot>/SfP

cd DfP
python infer.py --input-dir ./Datasets/PolaRGB --ckpt-dir <snapshot>/DfP \
  --polarfree-checkpoint-dir ./experiments/checkpoints/polarfree

The DfP workflow loads the PolarFree diffusion-prior files separately using their upstream filenames.

Data

• SfP dataset links are distributed through SfPUEL. Follow the dataset terms and citation guidance from the provider.
• DfP uses PolaRGB, distributed under CC BY-NC 4.0.

Integrity

SHA-256 checksums are provided in SHA256SUMS.txt.

Citation

If you use these model weights in your research, please cite:

@inproceedings{luo2026polarapp,
  title     = {PolarAPP: Beyond Polarization Demosaicking for Polarimetric Applications},
  author    = {Luo, Yidong and Li, Chenggong and Song, Yunfeng and Wang, Ping and Shi, Boxin and Zhang, Junchao and Yuan, Xin},
  booktitle = {European Conference on Computer Vision (ECCV)},
  series    = {Lecture Notes in Computer Science},
  volume    = {17024},
  pages     = {115--133},
  publisher = {Springer},
  address   = {Cham},
  year      = {2026},
  doi       = {10.1007/978-3-032-37556-8_7}
}