mlsanityData to 19 Oct 2026

Text-to-3D generation

268 papers0 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

Keywords: generation, text-to-, diffusion, text-to- generation, score

Key facts. Text-to-3D generation: 268 papers on arXiv since 2021 (data through 19 Oct 2026). 229 of its 268 mapped papers (85%) cite “DreamFusion: Text-to-3D using 2D Diffusion” (2022, arXiv 2209.14988). 3 new papers 1 Oct–19 Oct.

What’s new

1 Oct – 19 Oct 2026

3 new since 1 Oct

  1. HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution
  2. DynaMesh: Dynamic 3D Texture Generation
  3. STAGE: Subspace-Targeted Affine Generative Erasure for Text-to-3D Models

Foundations

Most cited by papers here

  1. DreamFusion: Text-to-3D using 2D Diffusion2022cited by 229 here
  2. Magic3D: High-Resolution Text-to-3D Content Creation2022cited by 189 here
  3. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation2023cited by 175 here
  4. Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation2023cited by 143 here
  5. Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures2022cited by 108 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 39 here
  2. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 100 here
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 229 here
  4. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 189 here
  5. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 143 here
  6. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 175 here
  7. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 67 here
  8. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 107 here
  9. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 59 here
15 more it builds on, not in this chain
  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 43 here
  2. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 38 here
  3. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 108 here
  4. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 111 here
  5. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 47 here
  6. 2023TextMesh: Generation of Realistic 3D Meshes From Text Promptscited by 41 here
  7. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 53 here
  8. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 57 here
  9. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 127 here
  10. 2023Text-to-3D using Gaussian Splattingcited by 54 here
  11. 2023SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3Dcited by 40 here
  12. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 51 here
  13. 2023Text-to-3D with Classifier Score Distillationcited by 38 here
  14. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 57 here
  15. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 48 here

The 24 most cited of 608.

Browse

30 of 268, ranked 6–35

  1. 6DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation2023107
  2. 7Zero-Shot Text-Guided Object Generation with Dream Fields2021100
  3. 8LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching202359
  4. 9Text-to-3D using Gaussian Splatting202354
  5. 10Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model202348
  6. 11TextMesh: Generation of Realistic 3D Meshes From Text Prompts202341
  7. 12SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D202340
  8. 13Text-to-3D with Classifier Score Distillation202338
  9. 14Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation202336
  10. 15ATT3D: Amortized Text-to-3D Object Synthesis202335
All 30
  1. 16DreamBooth3D: Subject-Driven Text-to-3D Generation202334
  2. 17GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models202334
  3. 18HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance202331
  4. 19RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D202328
  5. 20SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation202225
  6. 21Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models202225
  7. 22Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior202423
  8. 23T3Bench: Benchmarking Current Progress in Text-to-3D Generation202323
  9. 24GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting202420
  10. 25Compositional 3D Scene Generation using Locally Conditioned Diffusion202320
  11. 26Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer202417
  12. 27Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation202317
  13. 28Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields202316
  14. 293DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors202415
  15. 30Vox-E: Text-guided Voxel Editing of 3D Objects202315
  16. 31Control3D: Towards Controllable Text-to-3D Generation202315
  17. 32LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes202315
  18. 33IT3D: Improved Text-to-3D Generation with Explicit View Synthesis202314
  19. 34LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis202413
  20. 35DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior202313