Home

Awesome

Deep Material-aware Cross-spectral Stereo Matching

Tiancheng Zhi, Bernardo R. Pires, Martial Hebert, Srinivasa G. Narasimhan

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

[Project] [Paper] [Supp]

<p align="center"> <img src="imgs/teaser.png" width="800px"/> </p>

Disclaimer

This is an improved and simplified version of the CVPR code. Compared with the original CVPR version, this code achieves a better performance (see pretrained model below). Main changes include:

To compare with the original CVPR result, please refer to the project page (first download link to the dataset).

Requirements

Data

Download rgbnir_stereo, and move "data" and "lists" into the "cs-stereo" folder.

Download precomputed_material, and put it under the "cs-stereo" folder.

Then run:

sh cp_material.sh precomputed_material data

See project page for more information and downlad links of PittsStereo Dataset.

Training

CUDA_VISIBLE_DEVICES=1,0 python3 train.py

Testing

CUDA_VISIBLE_DEVICES=1,0 python3 test.py --ckpt-path ckpt/47.pth

Pretrained Model

Download pretrained.pth

Performance (RMSE, lower is better):

ModelCommonLightGlassGlossyVegetationSkinClothingBagMean
CVPR'180.530.690.650.700.721.151.150.800.80
Pretrained0.470.560.560.610.720.930.910.860.70