Papers › Learning Canonical Representations for Scene Graph to Image Generation

Learning Canonical Representations for Scene Graph to Image Generation

16 Dec 2019ECCV 2020 8arXiv:1912.07414archive 2025-07-28

Roei Herzig, Amir Bar, Huijuan Xu, Gal Chechik, Trevor Darrell, Amir Globerson

Generating realistic images of complex visual scenes becomes challenging when one wishes to control the structure of the generated images. Previous approaches showed that scenes with few entities can be controlled using scene graphs, but this approach struggles as the complexity of the graph (the number of objects and edges) increases. In this work, we show that one limitation of current methods is their inability to capture semantic equivalence in graphs. We present a novel model that addresses these issues by learning canonical graph representations from the data, resulting in improved image generation for complex visual scenes. Our model demonstrates improved empirical performance on large scene graphs, robustness to noise in the input scene graph, and generalization on semantically equivalent graphs. Finally, we show improved performance of the model on three different benchmarks: Visual Genome, COCO, and CLEVR.

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="1912.07414")

Code

Syntology Ran 2 of 17 code samples harvested from 1 repository linked to this paper; 15 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: official repository: 17 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

roeiherz/CanonicalSg2Im officialpytorchMIT report
roeiherz/AG2Video 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

17 samples harvested; 2 ran; 0 honoured the contract we drafted; 15 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 · our draft was wrong
15unverified

Licence: 0 of the 17 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 roeiherz/CanonicalSg2Im. “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.

build_mlp roeiherz/CanonicalSg2Im/sg2im/layers.py official repository ran · our draft was wrong MIT (permissive) · a193f189a7547b8b · report
get_activation roeiherz/CanonicalSg2Im/sg2im/layers.py official repository ran · our draft was wrong MIT (permissive) · 6adb3b06f471b25d · report
bce_loss roeiherz/CanonicalSg2Im/sg2im/losses.py official repository unverified MIT (permissive) · ae92b5ed5c527664 · report
build_cnn roeiherz/CanonicalSg2Im/sg2im/layers.py official repository unverified MIT (permissive) · d03b87199703534d · report
calculate_activation_statistics roeiherz/CanonicalSg2Im/evaluation/fid_tf.py official repository unverified MIT (permissive) · 6917ffcb1214d74f · report
calculate_activation_statistics roeiherz/CanonicalSg2Im/evaluation/fid/fid_score.py official repository unverified MIT (permissive) · 94ea5856a1451de8 · report
calculate_frechet_distance roeiherz/CanonicalSg2Im/evaluation/fid/fid_score.py official repository unverified MIT (permissive) · 0def50a351111624 · report
calculate_frechet_distance roeiherz/CanonicalSg2Im/evaluation/fid_tf.py official repository unverified MIT (permissive) · f82d43c86ff154eb · report
confusion_matrix roeiherz/CanonicalSg2Im/evaluation/fid.py official repository unverified MIT (permissive) · 590d417a313b8256 · report
gan_g_loss roeiherz/CanonicalSg2Im/sg2im/losses.py official repository unverified MIT (permissive) · bea7eab39b0f3e75 · report
get_activations roeiherz/CanonicalSg2Im/evaluation/fid_tf.py official repository unverified MIT (permissive) · e69fcd6206886931 · report
get_activations roeiherz/CanonicalSg2Im/evaluation/fid/fid_score.py official repository unverified MIT (permissive) · 868290905012e985 · report
get_conv_converse roeiherz/CanonicalSg2Im/sg2im/model.py official repository unverified MIT (permissive) · b117e70083ba7cf4 · report
get_gan_losses roeiherz/CanonicalSg2Im/sg2im/losses.py official repository unverified MIT (permissive) · ee94d6adfea70511 · report
get_predicates_weights roeiherz/CanonicalSg2Im/sg2im/graph.py official repository unverified MIT (permissive) · c1b8c34d251f28dd · report
kl roeiherz/CanonicalSg2Im/evaluation/fid.py official repository unverified MIT (permissive) · df860a11dd4c724c · report
quant roeiherz/CanonicalSg2Im/evaluation/fid.py official repository unverified MIT (permissive) · 83ba89f8767e1931 · report

Tasks

Image GenerationLayout-to-Image GenerationScene Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Layout-to-Image Generation COCO-Stuff 256x256 AttSPADE FID 54.7 #5 of 5 Archive leaderboard report
Layout-to-Image Generation COCO-Stuff 256x256 AttSPADE Inception Score 15.6 #5 of 5 Archive leaderboard report
Layout-to-Image Generation COCO-Stuff 256x256 AttSPADE LPIPS 0.44 #5 of 5 Archive leaderboard report
Layout-to-Image Generation Visual Genome 256x256 AttSPADE FID 36.4 #3 of 4 Archive leaderboard report
Layout-to-Image Generation Visual Genome 256x256 AttSPADE Inception Score 11 #3 of 4 Archive leaderboard report
Layout-to-Image Generation Visual Genome 256x256 AttSPADE LPIPS 0.51 #3 of 4 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.

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