Deep-Flow-Guided-Video-Inpainting icon indicating copy to clipboard operation
Deep-Flow-Guided-Video-Inpainting copied to clipboard

Published 20 hours ago • verified publisher icon nbei

Experimental Details

Open zengyh1900 opened this issue 5 years ago • 2 comments

The results are very impressive, I like it very much and thank you for sharing! Would you mind giving me more details as I missed them in your paper or this repo:

  1. What's the spatial size during training for each dataset (Youtube-VOS and DAVIS)?
  2. What's the spatial size for numeric evaluation and visual results shown in the paper for each dataset (Youtube-VOS and DAVIS)?
  3. How many frames of each testing video do you use for numeric evaluation?
  4. You said in the paper that you only use a subset of 90 videos of DAVIS for testing, would you mind sharing the list?
  5. Do you use all test split of YouTube-VOS for numeric evaluation?
  6. Actually, YouTube-VOS has dense object segmentation masks for training samples, why not split a subset from the training list for object removal evaluation?

Looking forward to your response and big thanks again!!

zengyh1900 avatar Aug 16 '19 08:08 zengyh1900

@nbei These are very important details to reproduce the results. Could you please share them? Thanks

leao1995 avatar Jan 07 '21 18:01 leao1995

Hi @leao1995, I will update the FAQ for your reference.

nbei avatar Jan 08 '21 02:01 nbei