Awesome

Parallax-Tolerant Unsupervised Deep Image Stitching (UDIS++ paper)

Lang Nie*, Chunyu Lin*, Kang Liao*, Shuaicheng Liu`, Yao Zhao* * Institute of Information Science, Beijing Jiaotong University ` School of Information and Communication Engineering, University of Electronic Science and Technology of China

Dataset (UDIS-D)

We use the UDIS-D dataset to train and evaluate our method. Please refer to UDIS for more details about this dataset.

Code

Requirement

numpy 1.19.5
pytorch 1.7.1
scikit-image 0.15.0
tensorboard 2.9.0

We implement this work with Ubuntu, 3090Ti, and CUDA11. Refer to environment.yml for more details.

How to run it

Similar to UDIS, we also implement this solution in two stages:

Stage 1 (unsupervised warp): please refer to Warp/readme.md.
Stage 2 (unsupervised composition): please refer to Composition/readme.md.

Meta

If you have any questions about this project, please feel free to drop me an email.

NIE Lang -- nielang@bjtu.edu.cn

@inproceedings{nie2023parallax,
  title={Parallax-Tolerant Unsupervised Deep Image Stitching},
  author={Nie, Lang and Lin, Chunyu and Liao, Kang and Liu, Shuaicheng and Zhao, Yao},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={7399--7408},
  year={2023}
}

References

[1] L. Nie, C. Lin, K. Liao, M. Liu, and Y. Zhao, “A view-free image stitching network based on global homography,” Journal of Visual Communication and Image Representation, p. 102950, 2020.
[2] L. Nie, C. Lin, K. Liao, and Y. Zhao. Learning edge-preserved image stitching from multi-scale deep homography[J]. Neurocomputing, 2022, 491: 533-543.
[3] L. Nie, C. Lin, K. Liao, S. Liu, and Y. Zhao. Unsupervised deep image stitching: Reconstructing stitched features to images[J]. IEEE Transactions on Image Processing, 2021, 30: 6184-6197.
[4] L. Nie, C. Lin, K. Liao, S. Liu, and Y. Zhao. Deep rectangling for image stitching: a learning baseline[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022: 5740-5748.