Implicit Neural Image Stitching With Enhanced and Blended Feature Reconstruction
This repository contains the official implementation of NIS, 24' WACV: https://arxiv.org/abs/2309.01409
Requirement
- Python packages
conda env create --file environment.yaml
conda activate nis
- pysrwarp : Follow guidelines in the repository for more details.
git clone https://github.com/sanghyun-son/pysrwarp
cd pysrwarp
make
Train & Evaluation
bash scripts/train.sh 0
bash scripts/eval.sh 0
Pretrained Models
You can download below models on this link.
- NIS_enhancing.pth: Pretrained on Enhanced Stitching (Stage 1),
- NIS_blending.pth: Pretrained on Enhanced & Blended Stitching (Stage 1 & 2),
- ihn.pth: Our reproduced Homography Estimator used in the second stage training.
Acknowlegment
This work is mainly based on LTEW and IHN, we thank the authors for the contribution.