Zhengxue Wang, Zhiqiang Yan✉, Jian Yang✉
PCA Lab, Nanjing University of Science and Technology, China
This repository is an official PyTorch implementation of our SGNet (AAAI 2024).
Python==3.11.5
PyTorch==2.1.0
numpy==1.23.5
torchvision==0.16.0
scipy==1.11.3
thop==0.1.1.post2209072238
Pillow==10.0.1
tqdm==4.65.0
All pretrained models can be found here. Please note that some variable names in the initial pretrained .pth files are not consistent with those in the latest code. Therefore, we have reuploaded the new .pth files for completeness, named xxx_R.pth.
python train.py --scale 4 --num_feats 48
python train.py --scale 8 --num_feats 40
python train.py --scale 16 --num_feats 40
python train.py --scale 4 --num_feats 24
python test.py --scale 4 --num_feats 48
python test.py --scale 8 --num_feats 40
python test.py --scale 16 --num_feats 40
python test.py --scale 4 --num_feats 24
Train & test on real-world RGB-D-D:
Train & test on synthetic NYU-v2 (x16): Train on NYU-v2, test on RGB-D-D (x16):We thank all reviewers for their professional and instructive suggestions.
We thank these repos sharing their codes: DKN and SUFT.
If our method proves to be of any assistance, please consider citing:
@inproceedings{wang2024sgnet,
title={Sgnet: Structure guided network via gradient-frequency awareness for depth map super-resolution},
author={Wang, Zhengxue and Yan, Zhiqiang and Yang, Jian},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={38},
number={6},
pages={5823--5831},
year={2024}
}