search

brandleyzhou / DIFFNet

[BMVC 2021] ''Self-Supervised Monocular Depth Estimation with Internal Feature Fusion''
109 stars 21 forks source link

test on video #27

Closed Hyyzhangrui closed 1 year ago

Hyyzhangrui commented 1 year ago

Hello, would like to ask you a question. The input to the model is a video, how to generate a video after a depth estimate? Can you tell me how to fix it? Thanks!

the best, Rui Zhang

brandleyzhou commented 1 year ago

Hi Rui,

The input to the model is a single image. if you want to generate corresponding depth from a video, you need first split the video into a set of frames, feeding them into the model separately. Then you can convert the generated depth maps to a gif or video file with some available tools.

Hang

Hyyzhangrui commented 1 year ago

Hi. Thank you very much for your quick reply. I'll go and finish it. Have a great life.

best, Rui