Papers › Image Generation from Scene Graphs

Image Generation from Scene Graphs

4 Apr 2018CVPR 2018 6arXiv:1804.01622archive 2025-07-28

Justin Johnson, Agrim Gupta, Li Fei-Fei

To truly understand the visual world our models should be able not only to recognize images but also generate them. To this end, there has been exciting recent progress on generating images from natural language descriptions. These methods give stunning results on limited domains such as descriptions of birds or flowers, but struggle to faithfully reproduce complex sentences with many objects and relationships. To overcome this limitation we propose a method for generating images from scene graphs, enabling explicitly reasoning about objects and their relationships. Our model uses graph convolution to process input graphs, computes a scene layout by predicting bounding boxes and segmentation masks for objects, and converts the layout to an image with a cascaded refinement network. The network is trained adversarially against a pair of discriminators to ensure realistic outputs. We validate our approach on Visual Genome and COCO-Stuff, where qualitative results, ablations, and user studies demonstrate our method's ability to generate complex images with multiple objects.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 21 code samples harvested from 1 repository linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 21 samples from 1 repository, 20 ran (20 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

cjpurackal/sg2im-tf mentioned on GitHubtfSyntology: not harvested report
google/sg2im mentioned on GitHubpytorchApache-2.0Syntology: 21 samples, 20 ran (0 instrument-failed) · 1 unverified report
roeiherz/AG2Video mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Compositional Video Synthesis with Action Graphs (arXiv:2006.15327; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
roeiherz/CanonicalSg2Im mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Canonical Representations for Scene Graph to Image Generation (arXiv:1912.07414; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

21 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

20ran
1unverified

Licence: 1 of the 21 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from google/sg2im. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

google/sg2im community (archive-listed) 21 samples, 20 ran (0 instrument-failed) · 1 unverified
apply_box_transform sg2im/box_utils.py ran fingerprinted Apache-2.0 (permissive) · bbfc6fccb2deb17b · report fixture: signature anchors:Tensor/2/float, transforms:Tensor/2/float · returned Tensor · level recorded 2026-09-26
bce_loss in 22 papers sg2im/losses.py ran fingerprinted Apache-2.0 (permissive) · ae92b5ed5c527664 · report fixture: signature input:Tensor/1/float, target:Tensor/1/float · returned Tensor · level recorded 2026-09-25
boxes_to_layout sg2im/layout.py ran Apache-2.0 (permissive) · f37f84bce6a380cf · report fixture: signature vecs:Tensor/2/float, boxes:Tensor/2/float, obj_to_img:Tensor/1/int, H:int/0/int, W:int/0/int, pooling:str/0/str · returned Tensor · level recorded 2026-09-26
build_cnn in 7 papers sg2im/layers.py ran Apache-2.0 (permissive) · be7d98c8795b76d3 · report fixture: signature arch:list/1/str, normalization:str/0/str, activation:str/0/str, padding:str/0/str, pooling:str/0/str, init:str/0/str · returned tuple · level recorded 2026-09-26
centers_to_extents sg2im/box_utils.py ran fingerprinted Apache-2.0 (permissive) · e511231aa813e416 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-26
crop_bbox sg2im/bilinear.py ran Apache-2.0 (permissive) · c8692f8992a3674d · report fixture: signature feats:Tensor/4/float, bbox:Tensor/2/float, HH:int/0/int, WW:int/0/int, backend:str/0/str · returned Tensor · level recorded 2026-09-26
crop_bbox_batch sg2im/bilinear.py ran Apache-2.0 (permissive) · 8688d7053f5c0967 · report fixture: signature feats:Tensor/4/float, bbox:Tensor/2/float, bbox_to_feats:Tensor/1/int, HH:int/0/int, WW:int/0/int · returned Tensor · level recorded 2026-09-26
crop_bbox_batch_cudnn sg2im/bilinear.py ran Apache-2.0 (permissive) · 7e52be356aeb8407 · report fixture: signature feats:Tensor/4/float, bbox:Tensor/2/float, bbox_to_feats:Tensor/1/int, HH:int/0/int, WW:int/0/int · returned Tensor · level recorded 2026-09-26
float_tuple sg2im/utils.py ran Apache-2.0 (permissive) · 5e3086197586c014 · report fixture: signature s:str/0/str · returned tuple · level recorded 2026-09-25
gan_g_loss sg2im/losses.py ran fingerprinted Apache-2.0 (permissive) · bea7eab39b0f3e75 · report fixture: signature scores_fake:Tensor/1/float · returned Tensor · level recorded 2026-09-25
get_activation in 218 papers sg2im/layers.py ran Apache-2.0 (permissive) · fa5f35b7c26dbe12 · report fixture: signature name:str/0/str · returned LeakyReLU · level recorded 2026-09-25
get_gan_losses sg2im/losses.py ran Apache-2.0 (permissive) · ee94d6adfea70511 · report fixture: signature gan_type:str/0/str · returned tuple · level recorded 2026-09-25
get_normalization_2d sg2im/layers.py ran Apache-2.0 (permissive) · 481b0a0e44bbea29 · report fixture: signature channels:int/0/int, normalization:str/0/str · returned BatchNorm2d · level recorded 2026-09-25
get_total_norm sg2im/metrics.py ran Apache-2.0 (permissive) · 86ef0f4c4c0c2702 · report fixture: signature parameters:list/1/Tensor, norm_type:int/0/int · returned Tensor · level recorded 2026-09-25
int_tuple in 6 papers sg2im/utils.py ran Apache-2.0 (permissive) · c7a0b110ef7c5e03 · report fixture: signature s:str/0/str · returned tuple · level recorded 2026-09-25
intersection in 24 papers sg2im/metrics.py ran fingerprinted Apache-2.0 (permissive) · 6d89e132179f2fbd · report fixture: signature bbox_pred:Tensor/2/float, bbox_gt:Tensor/2/float · returned Tensor · level recorded 2026-09-25
invert_box_transform sg2im/box_utils.py ran fingerprinted Apache-2.0 (permissive) · fc8f66fb9b6df96b · report fixture: signature anchors:Tensor/2/float, boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-26
jaccard in 33 papers sg2im/metrics.py ran fingerprinted Apache-2.0 (permissive) · 08186282213c3ffd · report fixture: signature bbox_pred:Tensor/2/float, bbox_gt:Tensor/2/float · returned Tensor · level recorded 2026-09-26
masks_to_layout sg2im/layout.py ran Apache-2.0 (permissive) · 9aaef561ce9bb1be · report fixture: signature vecs:Tensor/2/float, boxes:Tensor/2/float, masks:Tensor/3/float, obj_to_img:Tensor/1/int, H:int/0/int, W:int/0/int, pooling:str/0/str · returned Tensor · level recorded 2026-09-26
str_tuple sg2im/utils.py ran fingerprinted Apache-2.0 (permissive) · ec5493a698745a69 · report fixture: signature s:str/0/str · returned tuple · level recorded 2026-09-25
draw_scene_graph sg2im/vis.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 08c9ee87b8be3253 · report

Tasks

Image GenerationImage Generation from Scene GraphsLayout-to-Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Layout-to-Image Generation COCO-Stuff 64x64 SG2Im FID 67.96 #5 of 5 Archive leaderboard report
Layout-to-Image Generation COCO-Stuff 64x64 SG2Im Inception Score 7.3 #5 of 5 Archive leaderboard report
Layout-to-Image Generation Visual Genome 64x64 SG2Im FID 74.61 #4 of 4 Archive leaderboard report
Layout-to-Image Generation Visual Genome 64x64 SG2Im Inception Score 6.3 #4 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.

Methods

Convolution

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