Semantic Image Synthesis with Spatially-Adaptive Normalization · HackerPapers discussions

Semantic Image Synthesis with Spatially-Adaptive Normalization — mentioned by tmabraham

Fri, 25 Jun 2021 06:53:35 GMT

IDK why this is being downvoted, it was indeed published two year ago, they just apparently repackaged this as an easier-to-use tool: https://arxiv.org/abs/1903.07291

Paper and discussion history. A mention is not an endorsement.

Semantic Image Synthesis with Spatially-Adaptive Normalization — mentioned by czr

Sat, 08 Feb 2020 21:37:38 GMT

important to remember that header image is result of professional concept artist drawing over gaugan result (bottom left). explanation of paper is not awful but not great, would recommend to read the original https://arxiv.org/pdf/1903.07291.pdf

Paper and discussion history. A mention is not an endorsement.

Semantic Image Synthesis with Spatially-Adaptive Normalization — mentioned by codezero

Wed, 20 Mar 2019 14:30:11 GMT

Direct link to the paper here: https://arxiv.org/abs/1903.07291

Paper and discussion history. A mention is not an endorsement.

Semantic Image Synthesis with Spatially-Adaptive Normalization — mentioned by tonygrue

Tue, 19 Mar 2019 08:08:12 GMT

Paper here: https://arxiv.org/pdf/1903.07291.pdf Page 14 and beyond show a number of examples vs previous methods. IIUC, their contribution is a masking normalization layer (the 'SPADE' layer [see pg 4]) that allows the network to preserve the structure of the input segmentation/mask, leading to results quite a bit nicer than previous ones.

Paper and discussion history. A mention is not an endorsement.