mlsanityData to 14 Oct 2026

Text-to-3D Generation using Jensen-Shannon Score Distillation

arXiv 2503.10660 ↗First posted 8 Mar 2025cs.CV cs.AIcited by 2

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

Abstract (arXiv)

Score distillation sampling is an effective technique to generate 3D models from text prompts, utilizing pre-trained large-scale text-to-image diffusion models as guidance. However, the produced 3D assets tend to be over-saturating, over-smoothing, with limited diversity. These issues are results from a reverse Kullback-Leibler (KL) divergence objective, which makes the optimization unstable and results in mode-seeking behavior. In this paper, we derive a bounded score distillation objective based on Jensen-Shannon divergence (JSD), which stabilizes the optimization process and produces high-quality 3D generation. JSD can match well generated and target distribution, therefore mitigating mode seeking. We provide a practical implementation of JSD by utilizing the theory of generative adversarial networks to define an approximate objective function for the generator, assuming the discriminator is well trained. By assuming the discriminator following a log-odds classifier, we propose a minority sampling algorithm to estimate the gradients of our proposed objective, providing a practical implementation for JSD. We conduct both theoretical and empirical studies to validate our method. Experimental results on T3Bench demonstrate that our method can produce high-quality and diversified 3D assets.

Key facts. Cited by 2 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 79 of its 121 references that are in the map. First posted on arXiv 8 Mar 2025.

Builds on

79 of 121 references.

Closest ancestors · 19

Same direction, newest first

  1. 2024DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D Generation11 Sep
  2. 2024JointDreamer: Ensuring Geometry Consistency and Text Congruence in Text-to-3D Generation via Joint Score Distillation17 Jul
  3. 2024ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation2 Jul
  4. 2024Score Distillation via Reparametrized DDIM24 May
  5. 2024VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation25 Mar
  6. 2024DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation18 Mar
  7. 2024Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior14 Mar
  8. 2023CAD: Photorealistic 3D Generation via Adversarial Distillation11 Dec
  9. 2023RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D28 Nov
  10. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model10 Nov
  11. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  12. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization29 Jun
7 more
  1. 2023HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance30 May
  2. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  3. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation24 Mar
  4. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  5. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation1 Dec
  6. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  7. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 60

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  8. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  9. 2022Classifier-Free Diffusion Guidancecited by 5,847
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  11. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  12. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
38 more
  1. 2017Improved Training of Wasserstein GANscited by 2,235
  2. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,179
  3. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,045
  4. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  5. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  6. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  7. 2018Which Training Methods for GANs do actually Converge?cited by 679
  8. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  9. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  10. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  11. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  12. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
  13. 2022Diffusion-GAN: Training GANs with Diffusioncited by 205
  14. 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 153
  15. 2023Text-to-Image Diffusion Models are Zero-Shot Classifierscited by 143
  16. 2023Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusioncited by 131
  17. 2024ReNoise: Real Image Inversion Through Iterative Noisingcited by 128
  18. 2023ATT3D: Amortized Text-to-3D Object Synthesiscited by 87
  19. 2021Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscited by 74
  20. 2019On a generalization of the Jensen-Shannon divergence and the JS-symmetrization of distances relying on abstract meanscited by 61
  21. 2019Sliced Wasserstein Generative Modelscited by 61
  22. 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61
  23. 2017Multi-Agent Diverse Generative Adversarial Networkscited by 59
  24. 2024DreamReward: Text-to-3D Generation with Human Preferencecited by 56
  25. 2018Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effectcited by 49
  26. 20243D-HGS: 3D Half-Gaussian Splattingcited by 44
  27. 2024LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesiscited by 39
  28. 2023Don't Play Favorites: Minority Guidance for Diffusion Modelscited by 37
  29. 2023Taming Mode Collapse in Score Distillation for Text-to-3D Generationcited by 36
  30. 2023Stable Score Distillation for High-Quality 3D Generationcited by 27
  31. 2018Variational Inference with Tail-adaptive f-Divergencecited by 25
  32. 2024Your Diffusion Model is Secretly a Certifiably Robust Classifiercited by 24
  33. 2023SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identitycited by 23
  34. 2018MGGAN: Solving Mode Collapse using Manifold Guided Trainingcited by 22
  35. 2024Self-Guided Generation of Minority Samples Using Diffusion Modelscited by 19
  36. 2020Constraining Variational Inference with Geometric Jensen-Shannon Divergencecited by 17
  37. 2025Consistent Flow Distillation for Text-to-3D Generationcited by 17
  38. 2018MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generationcited by 15

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

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

2 papers.

  1. 2025Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infillingcited by 2
  2. 2026OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D
  2. 2025Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation
  3. 2025Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit Matching
  4. 2024VividDreamer: Invariant Score Distillation For Hyper-Realistic Text-to-3D Generation
  5. 2024Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior
  6. 2023Text-to-3D with Classifier Score Distillation
  7. 2024Flow Score Distillation for Diverse Text-to-3D Generation
  8. 2025Walking the Schr"odinger Bridge: A Direct Trajectory for Text-to-3D Generation