Papers › Semantic Image Synthesis with Spatially-Adaptive Normalization

Semantic Image Synthesis with Spatially-Adaptive Normalization

18 Mar 2019CVPR 2019 6arXiv:1903.07291archive 2025-07-28

Taesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu

We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the deep network, which is then processed through stacks of convolution, normalization, and nonlinearity layers. We show that this is suboptimal as the normalization layers tend to ``wash away'' semantic information. To address the issue, we propose using the input layout for modulating the activations in normalization layers through a spatially-adaptive, learned transformation. Experiments on several challenging datasets demonstrate the advantage of the proposed method over existing approaches, regarding both visual fidelity and alignment with input layouts. Finally, our model allows user control over both semantic and style. Code is available at https://github.com/NVlabs/SPADE .

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1903.07291")

Code

Syntology Ran 5 of 9 code samples harvested from 4 repositories linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 9 samples from 4 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

24 repositories listed; official and paper-mentioned ones first.

NVlabs/SPADE officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
Cold-Winter/BachGAN mentioned on GitHubpytorchNOASSERTION report
Dominioncher/smart-sketch mentioned on GitHubpytorchGPL-3.0 report
GrahamRigby/GauGanPlus mentioned on GitHubpytorch report
Kokonut133/MagicDraw mentioned on GitHubtf report
Kokonut133/frame2frame mentioned on GitHubtf report
LoganOneal/neuralpaint-server mentioned on GitHubpytorchGPL-3.0 report
divyanshj16/SPADE mentioned on GitHubpytorch report
manicman1999/StyleGAN-Keras mentioned on GitHub report
mindslab-ai/hififace mentioned on GitHubpytorch report
noyoshi/hacksc mentioned on GitHubpytorchGPL-3.0 report
noyoshi/smart-sketch mentioned on GitHubpytorchGPL-3.0 report
taki0112/SPADE-Tensorflow mentioned on GitHubtfMIT report
tamarott/ASAPNet mentioned on GitHubpytorch report
tinawu-23/smart-sketch mentioned on GitHubpytorch report
valeoai/SemanticPalette mentioned on GitHubpytorchNOASSERTION report
yeshwanth69/SPADE mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 5 ran; 2 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
1ran · fixture could not drive it
4unverified

Licence: 2 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

get_rand manicman1999/StyleGAN-Keras/stylegan.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 739a22fef98ba093 · report
noise manicman1999/StyleGAN-Keras/stylegan.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 62432992de807ab4 · report
noiseImage manicman1999/StyleGAN-Keras/stylegan.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · e5e3d7e6398e9f0f · report
noiseer GrahamRigby/GauGanPlus/Models.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · a4aac99f2ef193c4 · report
reparameterize GrahamRigby/GauGanPlus/Models.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · 26ebad4d064f2bf8 · report
load_segmap taki0112/SPADE-Tensorflow/utils.py community (archive-listed) unverified MIT (permissive) · e918f87e4b0b7abb · report
load_style_image taki0112/SPADE-Tensorflow/utils.py community (archive-listed) unverified MIT (permissive) · 19e181f299bf6f5c · report
preprocessing taki0112/SPADE-Tensorflow/utils.py community (archive-listed) unverified MIT (permissive) · eab7ba887c245523 · report
umeyama PacktPublishing/Hands-On-Image-Generation-with-TensorFlow-2.0/Chapter09/utils/umeyama.py community (archive-listed) unverified MIT (permissive) · 02ad9540c42e69f9 · report

Tasks

Image GenerationImage-to-Image TranslationSketch-to-Image Translation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image-to-Image Translation ADE20K Labels-to-Photos SPADE Accuracy 79.9% #8 of 16 Archive leaderboard report
Image-to-Image Translation ADE20K Labels-to-Photos SPADE FID 33.9 #8 of 16 Archive leaderboard report
Image-to-Image Translation ADE20K Labels-to-Photos SPADE LPIPS 0 #8 of 16 Archive leaderboard report
Image-to-Image Translation ADE20K Labels-to-Photos SPADE mIoU 38.5 #8 of 16 Archive leaderboard report
Image-to-Image Translation ADE20K-Outdoor Labels-to-Photos SPADE Accuracy 82.9% #3 of 7 Archive leaderboard report
Image-to-Image Translation ADE20K-Outdoor Labels-to-Photos SPADE FID 63.3 #3 of 7 Archive leaderboard report
Image-to-Image Translation ADE20K-Outdoor Labels-to-Photos SPADE mIoU 30.8 #3 of 7 Archive leaderboard report
Image-to-Image Translation COCO-Stuff Labels-to-Photos SPADE Accuracy 67.9% #10 of 15 Archive leaderboard report
Image-to-Image Translation COCO-Stuff Labels-to-Photos SPADE FID 22.6 #10 of 15 Archive leaderboard report
Image-to-Image Translation COCO-Stuff Labels-to-Photos SPADE mIoU 37.4 #10 of 15 Archive leaderboard report
Image-to-Image Translation Cityscapes Labels-to-Photo SPADE FID 71.8 #8 of 21 Archive leaderboard report
Image-to-Image Translation Cityscapes Labels-to-Photo SPADE Per-pixel Accuracy 81.9% #8 of 21 Archive leaderboard report
Image-to-Image Translation Cityscapes Labels-to-Photo SPADE mIoU 62.3 #8 of 21 Archive leaderboard report
Sketch-to-Image Translation COCO-Stuff SPADE FID 89.2 #3 of 3 Archive leaderboard report
Sketch-to-Image Translation COCO-Stuff SPADE FID-C 48.9 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: SPADE

SPADE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections