mlsanityData to 7 Oct 2026

Flow Score Distillation for Diverse Text-to-3D Generation

arXiv 2405.10988 ↗First posted 16 May 2024cs.LG cs.AIcited by 4

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

Abstract (arXiv)

Recent advancements in Text-to-3D generation have yielded remarkable progress, particularly through methods that rely on Score Distillation Sampling (SDS). While SDS exhibits the capability to create impressive 3D assets, it is hindered by its inherent maximum-likelihood-seeking essence, resulting in limited diversity in generation outcomes. In this paper, we discover that the Denoise Diffusion Implicit Models (DDIM) generation process (ie PF-ODE) can be succinctly expressed using an analogue of SDS loss. One step further, one can see SDS as a generalized DDIM generation process. Following this insight, we show that the noise sampling strategy in the noise addition stage significantly restricts the diversity of generation results. To address this limitation, we present an innovative noise sampling approach and introduce a novel text-to-3D method called Flow Score Distillation (FSD). Our validation experiments across various text-to-image Diffusion Models demonstrate that FSD substantially enhances generation diversity without compromising quality.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 49 of its 58 references that are in the map. First posted on arXiv 16 May 2024.

Builds on

49 of 58 references.

Closest ancestors · 14

Same direction, newest first

  1. 2023GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation29 Nov
  2. 2023Text-to-3D with Classifier Score Distillation30 Oct
  3. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusion23 Oct
  4. 2023Consistent123: Improve Consistency for One Image to 3D Object Synthesis12 Oct
  5. 2023Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models4 Oct
  6. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  7. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  8. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  9. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation24 Mar
  10. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  11. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation1 Dec
  12. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
2 more
  1. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep
  2. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  8. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  11. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  12. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
23 more
  1. 2016Improved Techniques for Training GANscited by 2,938
  2. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  3. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  4. 2023Consistency Modelscited by 1,778
  5. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  6. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  7. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  8. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  9. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  10. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
  11. 2023Preserve Your Own Correlation: A Noise Prior for Video Diffusion Modelscited by 284
  12. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 214
  13. 2023FreeNoise: Tuning-Free Longer Video Diffusion via Noise Reschedulingcited by 173
  14. 2022Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Modelscited by 172
  15. 2023Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyondcited by 139
  16. 2023Noise-Free Score Distillationcited by 99
  17. 2023BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrappingcited by 96
  18. 2017Improved Adversarial Systems for 3D Object Generation and Reconstructioncited by 66
  19. 2024Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Priorcited by 60
  20. 2018Learning Descriptor Networks for 3D Shape Synthesis and Analysiscited by 56
  21. 2021Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketchescited by 54
  22. 2023Taming Mode Collapse in Score Distillation for Text-to-3D Generationcited by 35
  23. 2023Stable Score Distillation for High-Quality 3D Generationcited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2025Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generationcited by 6
  2. 2024ModeDreamer: Mode Guiding Score Distillation for Text-to-3D Generation using Reference Image Promptscited by 2
  3. 2026Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preferencecited by 2
  4. 2025TriDiff-4D: Fast 4D Generation through Diffusion-based Triplane Re-posingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Diverse Score Distillation
  2. 2024A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D
  3. 2023Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting
  4. 2025Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation
  5. 2024Score Distillation via Reparametrized DDIM
  6. 2023StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D
  7. 2023DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
  8. 2023RL Dreams: Policy Gradient Optimization for Score Distillation based 3D Generation