This repository contains the official code and pretrained models for Line Segment Detection Using Transformers without Edges. Yifan Xu*, Weijian Xu*, David Cheung, and Zhuowen Tu. CVPR2021 (Oral)
In this paper, we present a joint end-to-end line segment detection algorithm using Transformers that is post-processing and heuristics-guided intermediate processing (edge/junction/region detection) free. Our method, named LinE segment TRansformers (LETR), takes advantages of having integrated tokenized queries, a self-attention mechanism, and encoding-decoding strategy within Transformers by skipping standard heuristic designs for the edge element detection and perceptual grouping processes. We equip Transformers with a multi-scale encoder/decoder strategy to perform fine-grained line segment detection under a direct endpoint distance loss. This loss term is particularly suitable for detecting geometric structures such as line segments that are not conveniently represented by the standard bounding box representations. The Transformers learn to gradually refine line segments through layers of self-attention.
05/07/2021: Code for LETR Basic Usage Demo are released.
04/30/2021: Code and pre-trained checkpoint for LETR are released.
Name | sAP10 | sAP15 | sF10 | sF15 | URL |
---|---|---|---|---|---|
Wireframe | 65.6 | 68.0 | 66.1 | 67.4 | LETR-R101 |
YorkUrban | 29.6 | 32.0 | 40.5 | 42.1 | LETR-R50 |
git clone https://github.com/mlpc-ucsd/LETR.git
mkdir -p data
mkdir -p evaluation/data
mkdir -p exp
conda create -n letr python anaconda
conda activate letr
conda install -c pytorch pytorch torchvision
conda install cython scipy
pip install -U 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
pip install docopt
To reproduce our results, you need to process two datasets, ShanghaiTech and YorkUrban. Files located at ./helper/wireframe.py and ./helper/york.py are both modified based on the code from L-CNN, which process the raw data from download.
- ShanghaiTech Train Data
- To Download (modified based on from L-CNN)
cd data bash ../helper/gdrive-download.sh 1BRkqyi5CKPQF6IYzj_dQxZFQl0OwbzOf wireframe_raw.tar.xz tar xf wireframe_raw.tar.xz rm wireframe_raw.tar.xz python ../helper/wireframe.py ./wireframe_raw ./wireframe_processed
- To Download (modified based on from L-CNN)
- YorkUrban Train Data
- To Download
cd data wget https://www.dropbox.com/sh/qgsh2audfi8aajd/AAAQrKM0wLe_LepwlC1rzFMxa/YorkUrbanDB.zip unzip YorkUrbanDB.zip python ../helper/york.py ./YorkUrbanDB ./york_processed
- To Download
- Processed Evaluation Data
bash ./helper/gdrive-download.sh 1T4_6Nb5r4yAXre3lf-zpmp3RbmyP1t9q ./evaluation/data/wireframe.tar.xz bash ./helper/gdrive-download.sh 1ijOXv0Xw1IaNDtp1uBJt5Xb3mMj99Iw2 ./evaluation/data/york.tar.xz tar -vxf ./evaluation/data/wireframe.tar.xz -C ./evaluation/data/. tar -vxf ./evaluation/data/york.tar.xz -C ./evaluation/data/. rm ./evaluation/data/wireframe.tar.xz rm ./evaluation/data/york.tar.xz
-
Train a coarse-model (a.k.a. stage1 model).
# Usage: bash script/*/*.sh [exp name] bash script/train/a0_train_stage1_res50.sh res50_stage1 # LETR-R50 bash script/train/a1_train_stage1_res101.sh res101_stage1 # LETR-R101
-
Train a fine-model (a.k.a. stage2 model).
# Usage: bash script/*/*.sh [exp name] bash script/train/a2_train_stage2_res50.sh res50_stage2 # LETR-R50 bash script/train/a3_train_stage2_res101.sh res101_stage2 # LETR-R101
-
Fine-tune the fine-model with focal loss (a.k.a. stage2_focal model).
# Usage: bash script/*/*.sh [exp name] bash script/train/a4_train_stage2_focal_res50.sh res50_stage2_focal # LETR-R50 bash script/train/a5_train_stage2_focal_res101.sh res101_stage2_focal # LETR-R101
- Evaluate models.
# Evaluate sAP^10, sAP^15, sF^10, sF^15 (both Wireframe and YorkUrban datasets). bash script/evaluation/eval_stage1.sh [exp name] bash script/evaluation/eval_stage2.sh [exp name] bash script/evaluation/eval_stage2_focal.sh [exp name]
If you use this code for your research, please cite our paper:
@article{xu2021line,
title={Line Segment Detection Using Transformers without Edges},
author={Xu, Yifan and Xu, Weijian and Cheung, David and Tu, Zhuowen},
journal={arXiv preprint arXiv:2101.01909},
year={2021}
}
This code is based on the implementations of DETR: End-to-End Object Detection with Transformers.