mlsanityData to 7 Oct 2026

SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations

arXiv 2206.14464 ↗First posted 29 Jun 2022cs.LG cs.AIcited by 1

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Score-based generative models (SGMs) show the state-of-the-art sampling quality and diversity. However, their training/sampling complexity is notoriously high due to the highly complicated forward/reverse processes, so they are not suitable for resource-limited settings. To solving this problem, learning a simpler process is gathering much attention currently. We present an enhanced GAN-based denoising method, called SPI-GAN, using our proposed straight-path interpolation definition. To this end, we propose a GAN architecture i) denoising through the straight-path and ii) characterized by a continuous mapping neural network for imitating the denoising path. This approach drastically reduces the sampling time while achieving as high sampling quality and diversity as SGMs. As a result, SPI-GAN is one of the best-balanced models among the sampling quality, diversity, and time for CIFAR-10, and CelebA-HQ-256.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 21 of its 25 references that are in the map. First posted on arXiv 29 Jun 2022.

Builds on

21 of 25 references.

Closest ancestors · 7

Same direction, newest first

  1. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  2. 2021Score-based Generative Modeling in Latent Space10 Jun
  3. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  4. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  6. 2020Denoising Diffusion Implicit Models6 Oct
  7. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 14

  1. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  6. 2016Improved Techniques for Training GANscited by 2,938
  7. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  8. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  9. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  10. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  11. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  12. 2020Adversarial Latent Autoencoderscited by 155
2 more
  1. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 122
  2. 2020Dual Contradistinctive Generative Autoencodercited by 58

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Reviewcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Latent Denoising Diffusion GAN: Faster sampling, Higher image quality
  2. 2023Insights into Closed-form IPM-GAN Discriminator Guidance for Diffusion Modeling
  3. 2023Semi-Implicit Denoising Diffusion Models (SIDDMs)
  4. 2023DiffFlow: A Unified SDE Framework for Score-Based Diffusion Models and Generative Adversarial Networks
  5. 2026GAN-Diff : Coupling Pretrained WGAN-GP Features with Conditional Diffusion U-Nets
  6. 2024Adv-KD: Adversarial Knowledge Distillation for Faster Diffusion Sampling
  7. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
  8. 2021Diffusion Models Beat GANs on Image Synthesis