ArbSR icon indicating copy to clipboard operation
ArbSR copied to clipboard

doubt regarding computation of LR space and HR space

Open nanmehta opened this issue 3 years ago • 2 comments

Hi thanks for your such interesting work, Can you please tell me why we need to subtract 0.5 and while calculating the coordinates in LR space. coor_h = ((coor_hr[0] + 0.5) / scale) - (torch.floor((coor_hr[0] + 0.5) / scale + 1e-3)) - 0.5

nanmehta avatar Nov 01 '21 05:11 nanmehta

Hi @nan-rock, please refer to Fig. 5(a) in the paper. Here, -0.5 is used to calculate L(x).

LongguangWang avatar Nov 03 '21 09:11 LongguangWang

Why 0.5 and not 0.4 or 0.6

On Wed, 3 Nov, 2021, 2:31 pm Longguang Wang, @.***> wrote:

Hi @nan-rock https://github.com/nan-rock, please refer to Fig. 5(a) in the paper. Here, -0.5 is used to calculate L(x).

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/LongguangWang/ArbSR/issues/14#issuecomment-958758203, or unsubscribe https://github.com/notifications/unsubscribe-auth/AQBI6BWMYAOLEQOGIHZV4ZDUKD247ANCNFSM5HDH3DZQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

-- *CONFIDENTIALITY NOTICE: The contents of this email message and any attachments are intended solely for the addressee(s) and may contain confidential and/or privileged information and may be legally protected from disclosure. If you are not the intended recipient of this message or their agent, or if this message has been addressed to you in error, please immediately alert the sender by reply email and then delete this message and any attachments. If you are not the intended recipient, you are hereby notified that any use, dissemination, copying, or storage of this message or its attachments is strictly prohibited.

nanmehta avatar Nov 03 '21 09:11 nanmehta