Hierarchical Deep Stereo Matching on High Resolution Images, CVPR 2019.
Qualitative results on Middlebury:
Performance on Middlebury benchmark (y-axis: error, the lower the better):
Able to handle large view variation of high-res images (as a submodule in Open4D, CVPR 2020):
Note: The .tar file can be directly loaded in pytorch. No need to uncompress it.
Test on CrusadeP and dancing stereo pairs:
CUDA_VISIBLE_DEVICES=3 python submission.py --datapath ./data-mbtest/ --outdir ./mboutput --loadmodel ./weights/final-768px.tar --testres 1 --clean 1.0 --max_disp -1
Evaluate on Middlebury additional images:
CUDA_VISIBLE_DEVICES=3 python submission.py --datapath ./path_to_additional_images --outdir ./output --loadmodel ./weights/final-768px.tar --testres 0.5
python eval_mb.py --indir ./output --gtdir ./groundtruth_path
Evaluate on HRRS:
CUDA_VISIBLE_DEVICES=3 python submission.py --datapath ./data-HRRS/ --outdir ./output --loadmodel ./weights/final-768px.tar --testres 0.5
python eval_disp.py --indir ./output --gtdir ./data-HRRS/
And use cvkit to visualize in 3D.
High-res-real-stereo (HR-RS) It has been taken off due to licensing issue. Please use the Argoverse dataset.
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --maxdisp 384 --batchsize 28 --database /d/ --logname log1 --savemodel /somewhere/ --epochs 10
@InProceedings{yang2019hsm,
author = {Yang, Gengshan and Manela, Joshua and Happold, Michael and Ramanan, Deva},
title = {Hierarchical Deep Stereo Matching on High-Resolution Images},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}
Part of the code is borrowed from MiddEval-SDK, PSMNet, FlowNetPytorch and pytorch-semseg. Thanks SorcererX for fixing version compatibility issues.