mlsanityData to 14 Oct 2026

On the Noise Scheduling for Generating Plausible Designs with Diffusion Models

arXiv 2311.11207 ↗First posted 19 Nov 2023cs.CV cs.AI cs.CEcited by 6

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Deep Generative Models (DGMs) are widely used to create innovative designs across multiple industries, ranging from fashion to the automotive sector. In addition to generating images of high visual quality, the task of structural design generation imposes more stringent constrains on the semantic expression, e.g., no floating material or missing part, which we refer to as plausibility in this work. We delve into the impact of noise schedules of diffusion models on the plausibility of the outcome: there exists a range of noise levels at which the model's performance decides the result plausibility. Also, we propose two techniques to determine such a range for a given image set and devise a novel parametric noise schedule for better plausibility. We apply this noise schedule to the training and sampling of the well-known diffusion model EDM and compare it to its default noise schedule. Compared to EDM, our schedule significantly improves the rate of plausible designs from 83.4% to 93.5% and Fr'echet Inception Distance (FID) from 7.84 to 4.87. Further applications of advanced image editing tools demonstrate the model's solid understanding of structure.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 27 of its 38 references that are in the map. First posted on arXiv 19 Nov 2023.

Builds on

27 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Models24 Jan

Other references · 26

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  8. 2013Auto-Encoding Variational Bayescited by 4,053
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  10. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  11. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  12. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
14 more
  1. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  2. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  3. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  4. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingcited by 294
  5. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 285
  6. 2014One weird trick for parallelizing convolutional neural networkscited by 264
  7. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 219
  8. 2017Stabilizing Training of Generative Adversarial Networks through Regularizationcited by 118
  9. 2021Deep Generative Models in Engineering Design: A Reviewcited by 105
  10. 2020Interacting particle solutions of Fokker-Planck equations through gradient-log-density estimationcited by 88
  11. 2020Airfoil Design Parameterization and Optimization using B'ezier Generative Adversarial Networkscited by 35
  12. 2022A Study on the Evaluation of Generative Modelscited by 35
  13. 2021BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarkscited by 27
  14. 2023Adversarial Latent Autoencoder with Self-Attention for Structural Image Synthesiscited by 5

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 1.

6 papers.

  1. 2024Elicitron: An LLM Agent-Based Simulation Framework for Design Requirements Elicitationcited by 19
  2. 2024NeuroNURBS: Learning Efficient Surface Representations for 3D Solidscited by 8
  3. 2024Fr'echet Denoised Distance: Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencodercited by 3
  4. 2024Exploring the Potentials and Challenges of Deep Generative Models in Product Design Conceptioncited by 3
  5. 2024GeoBiked: A Dataset with Geometric Features and Automated Labeling Techniques to Enable Deep Generative Models in Engineering Designcited by 2
  6. 2025A Mesh Is Worth 512 Numbers: Spectral-domain Diffusion Modeling for High-dimension Shape Generationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Structured Pattern Expansion with Diffusion Models
  2. 2022Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models
  3. 2024Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing
  4. 2023Latent Diffusion Models for Structural Component Design
  5. 2024Improved Noise Schedule for Diffusion Training
  6. 2023Guided Image Synthesis via Initial Image Editing in Diffusion Model
  7. 2022Markup-to-Image Diffusion Models with Scheduled Sampling
  8. 2022On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models