L-CNN — End-to-End Wireframe Parsing

This repository contains the official PyTorch implementation of the paper: Yichao Zhou, Haozhi Qi, Yi Ma. "End-to-End Wireframe Parsing." arXiv:1905.03246 [cs.CV].

Introduction

L-CNN is a conceptually simple yet effective neural network for detecting the wireframe from a given image. It outperforms the previous state-of-the-art wireframe and line detectors by a large margin. We hope that this repository serves as an easily reproducible baseline for future researches in this area.

Main Results

Qualitative Measures


LSD	AFM	Wireframe	L-CNN	Ground Truth

Quantitative Measures

The following table reports the performance metrics of several wireframe and line detectors on the Wireframe dataset.

| | Wireframe (sAP¹⁰) | Wireframe (AP^H) | Wireframe (F^H) | Wireframe (mAP^J) | | :--------------------------------------------------: | :--------------------------------: | :-----------------------------: | :----------------------------: | :------------------------------: | | LSD | / | 52.0 | 61.0 | / |
| AFM | 24.4 | 69.5 | 77.2 | 23.3 |
| Wireframe | 5.1 | 67.8 | 72.6 | 40.9 |
| L-CNN | 62.9 | 82.8 | 81.2 | 59.3 |

Precision-Recall Curves

Code Structure

Below is a quick overview of the function of each file.

########################### Data ###########################
figs/
data/                           # default folder for placing the data
    wireframe/                  # folder for Wireframe dataset (Huang et al.)
logs/                           # default folder for storing the output during training
########################### Code ###########################
config/                         # neural network hyper-parameters and configurations
    wireframe.yaml              # default parameter for Wireframe dataset
dataset/                        # all scripts related to data generation
    wireframe.py                # script for pre-processing the Wireframe dataset to npz
misc/                           # misc scripts that are not important
    draw-wireframe.py           # script for generating figure grids
    lsd.py                      # script for generating npz files for LSD
    plot-sAP.py                 # script for plotting sAP10 for all algorithms
lcnn/                           # lcnn module so you can "import lcnn" in other scripts
    models/                     # neural network structure
        hourglass_pose.py       # backbone network (stacked hourglass)
        line_vectorizer.py      # sampler and line verification network
        multitask_learner.py    # network for multi-task learning
    datasets.py                 # reading the training data
    metrics.py                  # functions for evaluation metrics
    trainer.py                  # trainer
    config.py                   # global variables for configuration
    utils.py                    # misc functions
eval-sAP.py                     # script for sAP evaluation
eval-APH.py                     # script for APH evaluation
eval-mAPJ.py                    # script for mAPJ evaluation
train.py                        # script for training the neural network
post.py                         # script for post-processing
process.py                      # script for processing a dataset from a checkpoint

Reproducing Results

Installation

For the ease of reproducibility, you are suggested to install miniconda (or anaconda if you prefer) before following executing the following commands.

git clone https://github.com/zhou13/lcnn
cd lcnn
conda create -y -n lcnn
source activate lcnn
# Replace cudatoolkit=10.0 with your CUDA version: https://pytorch.org/
conda install -y pytorch cudatoolkit=10.0 -c pytorch
conda install -y tensorboardx -c conda-forge
conda install -y pyyaml docopt matplotlib scikit-image opencv
mkdir data logs post

Downloading the Processed Dataset

Make sure curl is installed on your system and execute

cd data
../misc/gdrive-download.sh 1T4_6Nb5r4yAXre3lf-zpmp3RbmyP1t9q wireframe.tar.xz
tar xf wireframe.tar.xz
rm wireframe.tar.xz
cd ..

If gdrive-download.sh does not work for you, you can download the pre-processed dataset wireframe.tar.xz manually from Google Drive and proceed accordingly.

Processing the Dataset

Optionally, you can pre-process (e.g., generate heat maps, do data augmentation) the dataset from scratch rather than downloading the processed one. Skip this section if you just want to use the pre-processed dataset wireframe.tar.xz.

cd data
../misc/gdrive-download.sh 1BRkqyi5CKPQF6IYzj_dQxZFQl0OwbzOf wireframe_raw.tar.xz
tar xf wireframe_raw.tar.xz
rm wireframe_raw.tar.xz
cd ..
dataset/wireframe.py data/wireframe_raw data/wireframe

Training

To train the neural network on GPU 0 (specified by -d 0) with the default parameters, execute

python ./train.py -d 0 --identifier baseline  config/wireframe.yaml

Pre-trained Models

You can download our reference pre-trained models from Google Drive. This model was trained with config/wireframe.yaml for 312k iterations.

Post Processing

To post process the outputs from neural network (only necessary if you are going to evaluate AP^H), execute

python ./post.py --plot --thresholds="0.010,0.015" logs/RUN/npz/ITERATION post/RUN-ITERATION

where --plot is an optional argument to control whether the program should also generate images for visualization in addition to the npz files that contain the line information, and --thresholds controls how aggressive the post processing is. Multiple values in --thresholds is convenient for hyper-parameter search. You should replace RUN and ITERATION to the desired value of your training instance.

Evaluation

To evaluate the sAP (recommended) of all your checkpoints under logs/, execute

python eval-sAP.py logs/*/npz/*

To evaluate the mAP^J, execute

python eval-mAPJ.py logs/*/npz/*

To evaluate AP^H, you first need to post process your result (see the previous section). In addition, MATLAB is required for AP^H evaluation and matlab should be under your $PATH. The parallel computing toolbox is highly suggested due to the usage of parfor. After post processing, execute

python eval-APH.py post/RUN-ITERATION/0_010 post/RUN-ITERATION/0_010-APH

to get the plot, where 0_010 is the threshold used in the post processing, and post/RUN-ITERATION-APH is the temporary directory storing intermediate files. Due to the usage of pixel-wise matching, the evaluation of AP^H may take up to an hour depending on your CPUs.

See the source code of eval-sAP.py, eval-mAPJ.py, eval-APH.py, and misc/*.py for more details on evaluation.

Citing End-to-End Wireframe Parsing

If you find L-CNN useful in your research, please consider citing:

@article{zhou2019end,
  title={End-to-End Wireframe Parsing},
  author={Zhou, Yichao and Qi, Haozhi and Ma, Yi},
  journal={arXiv preprint arXiv:1905.03246},
  year={2019}
}

README.md 9.0 KB Cronologia Originale