</> Code with Papers by Syntology

Datasets › LSUN

LSUN (Large-scale Scene UNderstanding Challenge)

Introduced by Fisher Yu et al. in LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop1 Jan 2015 archive 2025-07-28

The Large-scale Scene Understanding (LSUN) challenge aims to provide a different benchmark for large-scale scene classification and understanding. The LSUN classification dataset contains 10 scene categories, such as dining room, bedroom, chicken, outdoor church, and so on. For training data, each category contains a huge number of images, ranging from around 120,000 to 3,000,000. The validation data includes 300 images, and the test data has 1000 images for each category.

Source: Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs Image Source: https://www.yf.io/p/lsun

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 10 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Image Generation LSUN Bedroom 256 x 256 Diffusion ProjectedGAN FID 1.43 Diffusion-GAN: Training GANs with Diffusion Zhendong-Wang/Diffusion-GAN +3 32 Compare
Image Generation LSUN Churches 256 x 256 Projected GAN FID 1.59 Projected GANs Converge Faster autonomousvision/projected_gan +2 27 Compare
Image Generation LSUN Cat 256 x 256 Vision-aided GAN FID 3.87 Ensembling Off-the-shelf Models for GAN Training nupurkmr9/vision-aided-gan 8 Compare
Image Generation LSUN Horse 256 x 256 Vision-aided GAN FID 2.15 Ensembling Off-the-shelf Models for GAN Training nupurkmr9/vision-aided-gan 6 Compare
Image Generation LSUN Bedroom StyleGAN FID-50k 2.65 A Style-Based Generator Architecture for Generative... NVlabs/stylegan +82 3 Compare
Image Generation LSUN Bedroom 64 x 64 WGAN-GP + TTUR + Alex-Adam FID 6.3 Fundamental Benefit of Alternating Updates in Minimax... hanseuljo/alex-gda 3 Compare
Image Generation LSUN Bedroom 128 x 128 LadaGAN FID 4.90 Efficient generative adversarial networks using linear... milmor/ladagan +1 2 Compare
Image Generation LSUN Car 512 x 384 Polarity-StyleGAN2 FID 2.27 Polarity Sampling: Quality and Diversity Control of... AhmedImtiazPrio/magnet-polarity 2 Compare
Image Generation LSUN BigGAN + gSR Average FID 20.18 Improving GANs for Long-Tailed Data through Group... val-iisc/gSRGAN 1 Compare
Image Generation LSUN Car 256 x 256 StyleGAN2 FID 2.32 Analyzing and Improving the Image Quality of StyleGAN labmlai/annotated_deep_learning_paper_implementations +125 1 Compare

Papers archive 2025-07-28

30 shown of 36 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 867. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction 1 1 30 Sep 2024 not harvested
Fundamental Benefit of Alternating Updates in Minimax Optimization 1 1 16 Feb 2024 ran 1 of 2 samples (1 unverified; 2 pointer-only for licence)
Efficient generative adversarial networks using linear additive-attention Transformers 2 1 17 Jan 2024 not harvested
Bellman Optimal Stepsize Straightening of Flow-Matching Models 1 2 27 Dec 2023 ran 8 of 14 samples (6 unverified; 14 pointer-only for licence)
Flow Matching in Latent Space 1 2 17 Jul 2023 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Wavelet Diffusion Models are fast and scalable Image Generators 1 1 29 Nov 2022 not harvested
StyleNAT: Giving Each Head a New Perspective 2 1 10 Nov 2022 ran 0 of 1 samples (1 unverified)
Improving GANs for Long-Tailed Data through Group Spectral Regularization 1 1 21 Aug 2022 ran 0 of 3 samples (3 unverified)
Diffusion-GAN: Training GANs with Diffusion 4 5 5 Jun 2022 ran 13 of 18 samples (5 unverified)
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values 1 3 3 Mar 2022 not harvested
Pseudo Numerical Methods for Diffusion Models on Manifolds 9 2 20 Feb 2022 ran 10 of 14 samples (4 unverified; 2 pointer-only for licence)
Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders 1 2 19 Feb 2022 ran 3 of 3 samples (0 unverified)
StyleSwin: Transformer-based GAN for High-resolution Image Generation 1 1 20 Dec 2021 ran 5 of 5 samples (0 unverified; 3 pointer-only for licence)
Ensembling Off-the-shelf Models for GAN Training 1 3 16 Dec 2021 ran 9 of 15 samples (6 unverified)
Tackling the Generative Learning Trilemma with Denoising Diffusion GANs 5 1 15 Dec 2021 ran 1 of 12 samples (11 unverified)
Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes 3 3 24 Nov 2021 not harvested
Projected GANs Converge Faster 3 5 1 Nov 2021 ran 38 of 49 samples (11 unverified; 6 pointer-only for licence)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation 1 1 10 Jun 2021 ran 4 of 12 samples (8 unverified)
Gotta Go Fast When Generating Data with Score-Based Models 1 2 28 May 2021 ran 2 of 3 samples (1 unverified; 3 pointer-only for licence)
Diffusion Models Beat GANs on Image Synthesis 21 4 11 May 2021 ran 27 of 50 samples (23 unverified; 16 pointer-only for licence)
Generative Adversarial Transformers 2 5 1 Mar 2021 ran 5 of 6 samples (1 unverified)
TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up 10 1 14 Feb 2021 ran 8 of 8 samples (0 unverified; 7 pointer-only for licence)
SWAGAN: A Style-based Wavelet-driven Generative Model 2 1 11 Feb 2021 ran 3 of 3 samples (0 unverified; 3 pointer-only for licence)
Image Generators with Conditionally-Independent Pixel Synthesis 2 1 27 Nov 2020 not harvested
Adversarial Generation of Continuous Images 1 1 24 Nov 2020 not harvested
Dual Contradistinctive Generative Autoencoder 0 1 19 Nov 2020 not harvested
Denoising Diffusion Probabilistic Models 70 6 19 Jun 2020 ran 178 of 253 samples (75 unverified; 62 pointer-only for licence)
Analyzing and Improving the Image Quality of StyleGAN 126 5 3 Dec 2019 ran 29 of 92 samples (63 unverified; 18 pointer-only for licence)
Sliced Wasserstein Generative Models 1 1 10 Apr 2019 not harvested
MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks 5 1 14 Mar 2019 ran 3 of 15 samples (12 unverified)

The full list of 36 is in the JSON twin.

Dataset loaders archive 2025-07-28

huggingface.co/datasets/detectors/lsun_c-oodhuggingface/datasetstfpytorchjax
huggingface.co/datasets/detectors/lsun_r-oodhuggingface/datasetstfpytorchjax
pytorch.org/vision/stable/generated/torchvision.datasets.LSUN.htmlpytorch/visionpytorch
www.tensorflow.org/datasets/catalog/lsuntensorflow/datasetstfjax

4 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Image Generation

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • LSUN Roon Layout
  • LSUN Bedroom 128 x 128
  • LSUN Bedroom
  • LSUN
  • LSUN Horse 256 x 256
  • LSUN Churches 256 x 256
  • LSUN Cat 256 x 256
  • LSUN Car 512 x 384
  • LSUN Car 256 x 256
  • LSUN Bedroom 64 x 64
  • LSUN Bedroom 256 x 256

11 variant names, as the archive lists them.

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