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 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="1804.01622")

Code

Syntology Ran 0 of 21 code samples harvested from 1 repository linked to this paper; 21 have no recorded run.

By repository: community (archive-listed): 21 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cjpurackal/sg2im-tf mentioned on GitHubtf report
google/sg2im mentioned on GitHubpytorchApache-2.0 report
roeiherz/AG2Video mentioned on GitHubpytorch report
roeiherz/CanonicalSg2Im mentioned on GitHubpytorchMIT 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

21 samples harvested; 0 ran; 0 honoured the contract we drafted; 21 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.

21unverified

Licence: 0 of the 21 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 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. “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.

apply_box_transform google/sg2im/sg2im/box_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · bbfc6fccb2deb17b · report
bce_loss google/sg2im/sg2im/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · ae92b5ed5c527664 · report
boxes_to_layout google/sg2im/sg2im/layout.py community (archive-listed) unverified Apache-2.0 (permissive) · f37f84bce6a380cf · report
build_cnn google/sg2im/sg2im/layers.py community (archive-listed) unverified Apache-2.0 (permissive) · be7d98c8795b76d3 · report
centers_to_extents google/sg2im/sg2im/box_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · e511231aa813e416 · report
crop_bbox google/sg2im/sg2im/bilinear.py community (archive-listed) unverified Apache-2.0 (permissive) · c8692f8992a3674d · report
crop_bbox_batch google/sg2im/sg2im/bilinear.py community (archive-listed) unverified Apache-2.0 (permissive) · 8688d7053f5c0967 · report
crop_bbox_batch_cudnn google/sg2im/sg2im/bilinear.py community (archive-listed) unverified Apache-2.0 (permissive) · 7e52be356aeb8407 · report
draw_scene_graph google/sg2im/sg2im/vis.py community (archive-listed) unverified Apache-2.0 (permissive) · 08c9ee87b8be3253 · report
float_tuple google/sg2im/sg2im/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 5e3086197586c014 · report
gan_g_loss google/sg2im/sg2im/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · bea7eab39b0f3e75 · report
get_activation google/sg2im/sg2im/layers.py community (archive-listed) unverified Apache-2.0 (permissive) · fa5f35b7c26dbe12 · report
get_gan_losses google/sg2im/sg2im/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · ee94d6adfea70511 · report
get_normalization_2d google/sg2im/sg2im/layers.py community (archive-listed) unverified Apache-2.0 (permissive) · 481b0a0e44bbea29 · report
get_total_norm google/sg2im/sg2im/metrics.py community (archive-listed) unverified Apache-2.0 (permissive) · 86ef0f4c4c0c2702 · report
int_tuple google/sg2im/sg2im/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · c7a0b110ef7c5e03 · report
intersection google/sg2im/sg2im/metrics.py community (archive-listed) unverified Apache-2.0 (permissive) · 6d89e132179f2fbd · report
invert_box_transform google/sg2im/sg2im/box_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · fc8f66fb9b6df96b · report
jaccard google/sg2im/sg2im/metrics.py community (archive-listed) unverified Apache-2.0 (permissive) · 08186282213c3ffd · report
masks_to_layout google/sg2im/sg2im/layout.py community (archive-listed) unverified Apache-2.0 (permissive) · 9aaef561ce9bb1be · report
str_tuple google/sg2im/sg2im/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · ec5493a698745a69 · 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