[CVPR 2020]CasMVSNet_Paddle复现

2. 参考资料

• CasMVSNet论文：Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
• Pytorch代码：alibaba/cascade-stereo

3. 训练代码

3.1 解压训练数据集

!rar x data/data129222/dtu_training.rar data/
!rm -rf data/data129222/dtu_training.rar 
!unzip -d data/mvs_training/dtu/Depths_raw data/data129777/Depths_raw1.zip!rm -rf data/data129777/Depths_raw1.zip !unzip -d data/mvs_training/dtu/Depths_raw data/data129777/Depths_raw2.zip!rm -rf data/data129777/Depths_raw2.zip '''
rar x data/data129222/dtu_training.rar data/
rm -rf data/data129222/dtu_training.rar 
unzip -d data/mvs_training/dtu/Depths_raw data/data129777/Depths_raw1.zip
rm -rf data/data129777/Depths_raw1.zip 
unzip -d data/mvs_training/dtu/Depths_raw data/data129777/Depths_raw2.zip
rm -rf data/data129777/Depths_raw2.zip 
'''

RAR 5.30 beta 2   Copyright (c) 1993-2015 Alexander Roshal   4 Aug 2015
Trial version             Type RAR -? for help

Cannot open data/data129222/dtu_training.rar
没有那个文件或目录
No files to extract
unzip:  cannot find or open data/data129777/Depths_raw1.zip, data/data129777/Depths_raw1.zip.zip or data/data129777/Depths_raw1.zip.ZIP.
unzip:  cannot find or open data/data129777/Depths_raw2.zip, data/data129777/Depths_raw2.zip.zip or data/data129777/Depths_raw2.zip.ZIP.

'\nrar x data/data129222/dtu_training.rar data/\nrm -rf data/data129222/dtu_training.rar \nunzip -d data/mvs_training/dtu/Depths_raw data/data129777/Depths_raw1.zip\nrm -rf data/data129777/Depths_raw1.zip \nunzip -d data/mvs_training/dtu/Depths_raw data/data129777/Depths_raw2.zip\nrm -rf data/data129777/Depths_raw2.zip \n'

3.2 开始训练

cd /home/aistudio/work/CasMVSNet_paddle/
!python train.py --dataset=dtu_yao --trainpath /home/aistudio/data/mvs_training/dtu/ --testpath /home/aistudio/data/mvs_training/dtu/ --trainlist lists/dtu/train.txt --testlist lists/dtu/test.txt --batch_size 2

4. 测试代码

4.1 解压测试数据集

!unzip -d data/ data/data129222/dtu_testing.zip

4.2 安装测试所需的包

!pip install plyfile

4.3 开始测试

cd /home/aistudio/work/CasMVSNet_paddle/
!python test.py --dataset=general_eval --batch_size=1 --testpath /home/aistudio/data/dtu_testing --testlist lists/dtu/test.txt --loadckpt ./log/model_000015.ckpt

5. 结果评估

• 由于测试需要MATLAB，所以需要将测试生成的PLY点云文件下载到本地，然后在本地评估。
• 评估的数据为DTU数据集，评估代码和数据：http://roboimagedata.compute.dtu.dk/?page_id=36

6. 结果展示

• 定量结果表明，复现成功。overall指标几乎没有差别。

  复现结果： acc.: 0.369 comp.:0.346 overall:0.357

  

  AdsGo AI

  全自动 AI 广告专家，助您在数分钟内完成广告搭建、优化及扩量

  下载

  原文结果： acc.: 0.325 comp.:0.385 overall:0.355

• 部分可视化结果展示：