AHupuJR / EFNet

Event-based Fusion for Motion Deblurring with Cross-modal Attention (ECCV'22 Oral) https://ahupujr.github.io/EFNet/
Other
137 stars 15 forks source link

Running EFNet on custom dataset #3

Open pentanol2 opened 1 year ago

pentanol2 commented 1 year ago

Hi, how to run EFNet on a custom dataset of video frames in which the root contains subfolders. Each subfolder contains frames of a separate video. The YAML configs we have here dont cover datasets of this type. You just mentioned the h5 hormat

AHupuJR commented 1 year ago

Hi, do you have events data with corresponding events?

pentanol2 commented 1 year ago

No, I dont. How to prepare that ?

AHupuJR commented 1 year ago

The event-based image reconstruction is different from image-only image reconstruction. I am not sure about your demands. Maybe you can search for some applications for event camera. And if you have a video dataset, you can prepare synthetic events using ESIM, https://github.com/uzh-rpg/rpg_esim. More information please refer to this link

Amore-HDU commented 1 year ago

Could you please tell me how to convert my own picture to h5?

Amore-HDU commented 1 year ago

And I want to know why convert picture to h5? thanks @AHupuJR