# Text-to-3D generation

Area: [3D reconstruction and neural rendering](https://mlsanity.com/recon3d/index.md). HTML: https://mlsanity.com/recon3d/text-to-3d-generation/

## 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).
- 189 of its 268 mapped papers (71%) cite “Magic3D: High-Resolution Text-to-3D Content Creation” (2022, arXiv 2211.10440).
- 3 new papers 1 Oct–19 Oct.

## Most cited here

- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022), cited by 229 papers here
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022), cited by 189 papers here
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023), cited by 175 papers here
- [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://mlsanity.com/paper/2303.13873/) (2023), cited by 143 papers here
- [Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures](https://mlsanity.com/paper/2211.07600/) (2022), cited by 108 papers here
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023), cited by 107 papers here
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021), cited by 100 papers here
- [LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching](https://mlsanity.com/paper/2311.11284/) (2023), cited by 59 papers here
- [Text-to-3D using Gaussian Splatting](https://mlsanity.com/paper/2309.16585/) (2023), cited by 54 papers here
- [Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model](https://mlsanity.com/paper/2311.06214/) (2023), cited by 48 papers here

## New (1 Oct–19 Oct)

- [HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution](https://mlsanity.com/paper/2610.11685/) (2026-10-08)
- [DynaMesh: Dynamic 3D Texture Generation](https://mlsanity.com/paper/2610.05529/) (2026-10-04)
- [STAGE: Subspace-Targeted Affine Generative Erasure for Text-to-3D Models](https://mlsanity.com/paper/2610.01302/) (2026-10-01)