LoFTR yang Efisien: Pencocokan Fitur Lokal Semi-Padat dengan Kecepatan Seperti Jarang
Yifan Wang * , Xingyi He * , Sida Peng, Dongli Tan, Xiaowei Zhou
CVPR 2024
conda env create -f environment.yaml
conda activate eloftr
pip install torch==2.0.0+cu118 --index-url https://download.pytorch.org/whl/cu118
pip install -r requirements.txt
Tes dan pelatihan dapat diunduh melalui link download yang disediakan oleh LoFTR
Kami menyediakan model terlatih kami di tautan unduhan
Anda perlu menyiapkan subset pengujian ScanNet dan MegaDepth terlebih dahulu. Kami membuat symlink dari kumpulan data yang diunduh sebelumnya ke data/{{dataset}}/test
.
# set up symlinks
ln -s /path/to/scannet-1500-testset/ * /path/to/EfficientLoFTR/data/scannet/test
ln -s /path/to/megadepth-1500-testset/ * /path/to/EfficientLoFTR/data/megadepth/test
conda activate eloftr
bash scripts/reproduce_test/indoor_full_time.sh
bash scripts/reproduce_test/indoor_opt_time.sh
conda activate eloftr
bash scripts/reproduce_test/outdoor_full_auc.sh
bash scripts/reproduce_test/outdoor_opt_auc.sh
bash scripts/reproduce_test/indoor_full_auc.sh
bash scripts/reproduce_test/indoor_opt_auc.sh
conda env create -f environment_training.yaml # used a different version of pytorch, maybe slightly different from the inference environment
pip install -r requirements.txt
conda activate eloftr_training
bash scripts/reproduce_train/eloftr_outdoor.sh eloftr_outdoor
Jika Anda merasa kode ini berguna untuk penelitian Anda, silakan gunakan entri BibTeX berikut.
@inproceedings { wang2024eloftr ,
title = { {Efficient LoFTR}: Semi-Dense Local Feature Matching with Sparse-Like Speed } ,
author = { Wang, Yifan and He, Xingyi and Peng, Sida and Tan, Dongli and Zhou, Xiaowei } ,
booktitle = { CVPR } ,
year = { 2024 }
}