New: we provide file parts in Baidu Drive now. If you cannot download because of this, try these links: Sony (25 GB) and Fuji (52 GB). There is download limit by Google drive in a fixed period of time. You can download it directly from Google drive for the Sony (25 GB) and Fuji (52 GB) sets. Please remove those images for quantitative results, but they still can be used for qualitative evaluations. Update Aug, 2018: We found some misalignment with the ground-truth for image 10034, 10045, 10172. CPU mode should also work with minor changes but not tested. Tested in Ubuntu + Intel i7 CPU + Nvidia Titan X (Pascal) with Cuda (>=8.0) and CuDNN (>=5.0). Required python (version 2.7) libraries: Tensorflow (>=1.1) + Scipy + Numpy + Rawpy.
This code includes the default model for training and testing on the See-in-the-Dark (SID) dataset.
This is a Tensorflow implementation of Learning to See in the Dark in CVPR 2018, by Chen Chen, Qifeng Chen, Jia Xu, and Vladlen Koltun.
0 kommentar(er)
