mlsanityData to 14 Oct 2026

Noise-Free Score Distillation

arXiv 2310.17590 ↗First posted 26 Oct 2023cs.CVcited by 99

Not on the map. Why?

Cited by 46 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Score Distillation Sampling (SDS) has emerged as the de facto approach for text-to-content generation in non-image domains. In this paper, we reexamine the SDS process and introduce a straightforward interpretation that demystifies the necessity for large Classifier-Free Guidance (CFG) scales, rooted in the distillation of an undesired noise term. Building upon our interpretation, we propose a novel Noise-Free Score Distillation (NFSD) process, which requires minimal modifications to the original SDS framework. Through this streamlined design, we achieve more effective distillation of pre-trained text-to-image diffusion models while using a nominal CFG scale. This strategic choice allows us to prevent the over-smoothing of results, ensuring that the generated data is both realistic and complies with the desired prompt. To demonstrate the efficacy of NFSD, we provide qualitative examples that compare NFSD and SDS, as well as several other methods.

Key facts. Cited by 99 papers in the map (data through 14 Oct 2026). Builds on 28 of its 33 references that are in the map. First posted on arXiv 26 Oct 2023.

Builds on

28 of 33 references.

References · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  10. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  11. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  12. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
16 more
  1. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  2. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  3. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
  4. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 694
  5. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 687
  6. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  7. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  8. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  9. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  10. 2023TextMesh: Generation of Realistic 3D Meshes From Text Promptscited by 135
  11. 2023Delta Denoising Scorecited by 121
  12. 2022VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Modelscited by 112
  13. 2023HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidancecited by 110
  14. 2023DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generationcited by 81
  15. 2023Word-As-Image for Semantic Typographycited by 63
  16. 2023DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusioncited by 26

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 11; 2024: 48; 2025: 35; 2026: 5.

99 papers.

Sort:

By area:

  1. 2023Adversarial Diffusion Distillationcited by 759
  2. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
  3. 2023Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Modelscited by 169
  4. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  5. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 154
  6. 2024Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidancecited by 113
  7. 2023HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splattingcited by 89
  8. 2024IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generationcited by 84
  9. 2024TC4D: Trajectory-Conditioned Text-to-4D Generationcited by 77
  10. 2023GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learningcited by 63
  11. 2024DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representationcited by 58
  12. 2024TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusioncited by 52
38 more
  1. 2024Director3D: Real-world Camera Trajectory and 3D Scene Generation from Textcited by 50
  2. 2026Lyra 2.0: Explorable Generative 3D Worldscited by 44
  3. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 43
  4. 2024Score Distillation via Reparametrized DDIMcited by 41
  5. 2025Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillationcited by 41
  6. 2024Text-to-Image Rectified Flow as Plug-and-Play Priorscited by 38
  7. 2024Rethinking Score Distillation as a Bridge Between Image Distributionscited by 38
  8. 2024PALP: Prompt Aligned Personalization of Text-to-Image Modelscited by 35
  9. 2024HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splattingcited by 35
  10. 2024LLMs Meet Multimodal Generation and Editing: A Surveycited by 35
  11. 2025Accelerated Diffusion Models via Speculative Samplingcited by 31
  12. 2023Stable Score Distillation for High-Quality 3D Generationcited by 27
  13. 2024Score Distillation Sampling with Learned Manifold Correctivecited by 27
  14. 2025DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimizationcited by 27
  15. 2024Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splattingcited by 26
  16. 2025Generating Physically Stable and Buildable Brick Structures from Textcited by 24
  17. 2024Diffusion Time-step Curriculum for One Image to 3D Generationcited by 21
  18. 2024Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabricationcited by 20
  19. 2024Connecting Consistency Distillation to Score Distillation for Text-to-3D Generationcited by 18
  20. 2024Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representationcited by 17
  21. 2024FreeCompose: Generic Zero-Shot Image Composition with Diffusion Priorcited by 16
  22. 2024PLA4D: Pixel-Level Alignments for Text-to-4D Gaussian Splattingcited by 15
  23. 2024Repulsive Latent Score Distillation for Solving Inverse Problemscited by 15
  24. 2024VividDreamer: Invariant Score Distillation For Hyper-Realistic Text-to-3D Generationcited by 15
  25. 2024DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservationcited by 14
  26. 2023Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusioncited by 13
  27. 2024Text-to-3D Shape Generationcited by 13
  28. 2025Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenizationcited by 13
  29. 2024DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusioncited by 12
  30. 2024DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusioncited by 12
  31. 2024InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillationcited by 12
  32. 2024Text2Place: Affordance-aware Text Guided Human Placementcited by 11
  33. 2023StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3Dcited by 10
  34. 2024TrAME: Trajectory-Anchored Multi-View Editing for Text-Guided 3D Gaussian Splatting Manipulationcited by 10
  35. 2025UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collectionscited by 10
  36. 2024Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusioncited by 9
  37. 2024ClotheDreamer: Text-Guided Garment Generation with 3D Gaussianscited by 9
  38. 2024DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D Generationcited by 9

50 most cited of 99 All 99 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation
  2. 2025Few-Step Diffusion via Score identity Distillation
  3. 2025Harnessing the Power of Training-Free Techniques in Text-to-2D Generation for Text-to-3D Generation via Score Distillation Sampling
  4. 2025Classifier-free Guidance with Adaptive Scaling
  5. 2025Dynamic Classifier-Free Diffusion Guidance via Online Feedback
  6. 2023Text-to-3D with Classifier Score Distillation
  7. 2024A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D
  8. 2025Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models