search

piiswrong / deep3d

Automatic 2D-to-3D Video Conversion with CNNs
1.25k stars 248 forks source link

Tensorflow Re-Implementation #44

Open MahmoudSelmy opened 6 years ago

MahmoudSelmy commented 6 years ago

Hello, I'm currently implementing your great in TF using the official params but the output is so bad and i don't know why ? Could you please give me any advice to make the output better? input> image output> output

CedricMx commented 6 years ago

i used mxnet-0.7.0, cuda8,cudnn5,but result is not same as author's, the right eye images is so blur, Does somebody have good results? please talk about your environment and application version

n1ckfg commented 6 years ago

I think it might make more sense to extract a depth map and generate two distorted images

wbhu commented 5 years ago

Hi @MahmoudSelmy . Could you please tell me Where to find the training data. Thank you very much