Unconditional Image Generation

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 37 papers with code (73 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• High-Resolution Image Synthesis with Latent Diffusion Models
  20 Dec 2021 41 repositories listed Syntology ran 19 of 28 samples · 9 unverified · 5 pointer-only (licence)
  By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
• Score-Based Generative Modeling through Stochastic Differential Equations
  26 Nov 2020 15 repositories listed Syntology ran 15 of 23 samples · 8 unverified · 4 pointer-only (licence)
  Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9.
• Large Scale Adversarial Representation Learning
  4 Jul 2019 4 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  We extensively evaluate the representation learning and generation capabilities of these BigBiGAN models, demonstrating that these generation-based models achieve the state of the art in unsupervised representation…
• Normalizing Flows are Capable Generative Models
  9 Dec 2024 3 repositories listed Syntology ran 1 of 4 samples · 3 unverified · 1 pointer-only (licence)
  Normalizing Flows (NFs) are likelihood-based models for continuous inputs.
• Fréchet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets
  2 Dec 2024 3 repositories listed
  Currently, metrics used for this task either rely on the (potentially biased) choice of some downstream task, such as segmentation, or adopt task-independent perceptual metrics (e.
• Adaptive Weighted Discriminator for Training Generative Adversarial Networks
  5 Dec 2020 3 repositories listed
  Generative adversarial network (GAN) has become one of the most important neural network models for classical unsupervised machine learning.
• Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
  19 Oct 2024 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 1 pointer-only (licence)
  SiDA utilizes the encoder from the generator's score network as a discriminator, allowing it to distinguish between real images and those generated by SiD.
• Efficient Diffusion Training via Min-SNR Weighting Strategy
  16 Mar 2023 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 2 pointer-only (licence)
  Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence.
• Manifold Matching via Deep Metric Learning for Generative Modeling
  20 Jun 2021 2 repositories listed
  We propose a manifold matching approach to generative models which includes a distribution generator (or data generator) and a metric generator.
• Negative Data Augmentation
  9 Feb 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities.
• Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
  28 Nov 2020 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  While Generative Adversarial Networks (GANs) show increasing performance and the level of realism is becoming indistinguishable from natural images, this also comes with high demands on data and computation.
• AutoGAN: Neural Architecture Search for Generative Adversarial Networks
  11 Aug 2019 2 repositories listed Syntology ran 1 of 5 samples · 4 unverified
  Neural architecture search (NAS) has witnessed prevailing success in image classification and (very recently) segmentation tasks.
• Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
  16 Oct 2024 1 repository listed Syntology ran 3 of 5 samples · 2 unverified
  Furthermore, we propose a simple but effective discrete image tokenizer to stabilize the latent space for image generative modeling by applying K-Means on the latent features of self-supervised learning models.
• Edge-preserving noise for diffusion models
  2 Oct 2024 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Classical generative diffusion models learn an isotropic Gaussian denoising process, treating all spatial regions uniformly, thus neglecting potentially valuable structural information in the data.
• Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models
  6 Apr 2024 1 repository listed Syntology ran 9 of 11 samples · 2 unverified · 11 pointer-only (licence)
  Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields.
• Diversity-aware Channel Pruning for StyleGAN Compression
  20 Mar 2024 1 repository listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Specifically, by assessing channel importance based on their sensitivities to latent vector perturbations, our method enhances the diversity of samples in the compressed model.
• WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis
  29 Feb 2024 1 repository listed
  Due to the three-dimensional nature of CT- or MR-scans, generative modeling of medical images is a particularly challenging task.
• Erasing Undesirable Influence in Diffusion Models
  11 Jan 2024 1 repository listed Syntology ran 11 of 12 samples · 1 unverified · 12 pointer-only (licence)
  Diffusion models are highly effective at generating high-quality images but pose risks, such as the unintentional generation of NSFW (not safe for work) content.
• Return of Unconditional Generation: A Self-supervised Representation Generation Method
  6 Dec 2023 1 repository listed Syntology ran 12 of 18 samples · 6 unverified
  This gap can be attributed to the lack of semantic information provided by labels.
• Diffusion Models for Constrained Domains
  11 Apr 2023 1 repository listed
  Denoising diffusion models are a novel class of generative algorithms that achieve state-of-the-art performance across a range of domains, including image generation and text-to-image tasks.
• Binary Latent Diffusion
  10 Apr 2023 1 repository listed
  In this paper, we show that a binary latent space can be explored for compact yet expressive image representations.
• Denoising Diffusion Autoencoders are Unified Self-supervised Learners
  17 Mar 2023 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training.
• Fast Inference in Denoising Diffusion Models via MMD Finetuning
  19 Jan 2023 1 repository listed Syntology ran 6 of 13 samples · 7 unverified
  Our findings show that the proposed method is able to produce high-quality samples in a fraction of the time required by widely-used diffusion models, and outperforms state-of-the-art techniques for accelerated sampling.
• RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
  17 Nov 2022 1 repository listed
  In this paper, we present RenderDiffusion, the first diffusion model for 3D generation and inference, trained using only monocular 2D supervision.
• MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
  16 Nov 2022 1 repository listed
  In this work, we propose MAsked Generative Encoder (MAGE), the first framework to unify SOTA image generation and self-supervised representation learning.
• Recursive Reasoning in Minimax Games: A Level k Gradient Play Method
  29 Oct 2022 1 repository listed
  Despite the success of generative adversarial networks (GANs) in generating visually appealing images, they are notoriously challenging to train.
• Generator Knows What Discriminator Should Learn in Unconditional GANs
  27 Jul 2022 1 repository listed
  Here we explore the efficacy of dense supervision in unconditional generation and find generator feature maps can be an alternative of cost-expensive semantic label maps.
• The ArtBench Dataset: Benchmarking Generative Models with Artworks
  22 Jun 2022 1 repository listed
  We introduce ArtBench-10, the first class-balanced, high-quality, cleanly annotated, and standardized dataset for benchmarking artwork generation.
• PAGER: Progressive Attribute-Guided Extendable Robust Image Generation
  1 Jun 2022 1 repository listed
  PAGER consists of three modules: core generator, resolution enhancer, and quality booster.
• Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values
  3 Mar 2022 1 repository listed
  We present Polarity Sampling, a theoretically justified plug-and-play method for controlling the generation quality and diversity of pre-trained deep generative networks DGNs).

Syntology lines on 17 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.