Embedded Files
Yukyung Choi* (KAIST), Namil Kim* (KAIST), Soonmin Hwang* (KAIST), Jongchan Park (KAIST), In So Kweon (KAIST)
TEN: Resolution Enhancer
TEN: Resolution Enhancer
The "SuperResolution benchmark" consists of 57 training image pairs and 10 test image pairs, saved in loss less png format. Since thermal images are provided in 16 bits format, we converted to 8 bits level to test and visualize the data. Note that we use a clipped linear mapping approaches for the contrast enhancement of thermal image as a pre-processing.
- download RGB91 for training
- download MSD(Multimodal Stereo Dataset) for training
- download TSD(Thermal Stereo Dataset) for training
- download RGBT67 for test*
- download stereo-calibration files
- download baseline code
Evaluation
Evaluation
Related Dataset
Related Dataset
- [TSD] Pedestrian Counting with Occlusion Handling Using Stereo Thermal Cameras, Sensors 2016.
- [MSD] CVC Multimodal Stereo Dataset, PR Letters 2013
Related Work
Related Work
- Brightness-based Convolutional Neural Network for Thermal Image Enhancement, IEEE Access 2017.
Citation
Citation
- When using this CNN model in your research, we will be happy if you cite us:
@INPROCEEDINGS{7759059, author={Y. Choi and N. Kim and S. Hwang and I. S. Kweon}, booktitle={2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, title={Thermal Image Enhancement using Convolutional Neural Network}, year={2016}, pages={223-230}, month={Oct},}Award
Award
- 1st place in NVidia Deep Learning Contest 2016. [link]
Google Sites
Report abuse