Papers › Semantic Bottleneck Scene Generation

Semantic Bottleneck Scene Generation

26 Nov 2019arXiv:1911.11357archive 2025-07-28

Samaneh Azadi, Michael Tschannen, Eric Tzeng, Sylvain Gelly, Trevor Darrell, Mario Lucic

Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottleneck GAN model for unconditional synthesis of complex scenes. We assume pixel-wise segmentation labels are available during training and use them to learn the scene structure. During inference, our model first synthesizes a realistic segmentation layout from scratch, then synthesizes a realistic scene conditioned on that layout. For the former, we use an unconditional progressive segmentation generation network that captures the distribution of realistic semantic scene layouts. For the latter, we use a conditional segmentation-to-image synthesis network that captures the distribution of photo-realistic images conditioned on the semantic layout. When trained end-to-end, the resulting model outperforms state-of-the-art generative models in unsupervised image synthesis on two challenging domains in terms of the Frechet Inception Distance and user-study evaluations. Moreover, we demonstrate the generated segmentation maps can be used as additional training data to strongly improve recent segmentation-to-image synthesis networks.

PaperPDFCode

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

Code

azadis/SB-GAN officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
liorfrenkel1992/SB-GAN mentioned on GitHubpytorchNOASSERTION 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Conditional Image GenerationImage GenerationImage-to-Image TranslationScene GenerationSegmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ADE-Indoor SB-GAN FID 85.27 #3 of 3 Archive leaderboard report
Image Generation Cityscapes-25K 256x512 SB-GAN FID 62.97 #1 of 1 Archive leaderboard report
Image Generation Cityscapes-5K 256x512 SB-GAN FID 65.49 #1 of 1 Archive leaderboard report
Image-to-Image Translation ADE-Indoor Labels-to-Photo SB-GAN FID 48.15 #1 of 1 Archive leaderboard report
Image-to-Image Translation Cityscapes Labels-to-Photo SB-GAN FID 60.39 #15 of 21 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