search

yzcjtr / GeoNet

Code for GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose (CVPR 2018)
MIT License
723 stars 181 forks source link

single view depth prediciton #13

Closed tongpinmo closed 6 years ago

tongpinmo commented 6 years ago

hello ,I have some doubts. Have you tried to use more than one images as input to predict depth or what's the advantages and significance of singe-view depth prediction? From some discussion, there is no true depth for a single image. one more,I think that single view depth has more problems generalizing to previously unseen types of images. For example ,a model trained on outdoor driving sequences is unlikely to work well on indoor scenes ? what do you think of them ?

yzcjtr commented 6 years ago

I haven't tried using two or more images as input to DepthNet. Of course you can try it. Promisingly you will have better generalization ability, but there is no guarantee. PS, I don't know what you exactly mean by 'there is no true depth for a single image'.

tongpinmo commented 6 years ago

ok, there is no true depth for a single image means that one single image input ,we can't get the real depth of an image.