Skip to main content

Research · Technical

DreamFusion: Text-to-3D Using 2D Diffusion

ICLR 2023 · Poole, B., Jain, A., Barron, J. T., Mildenhall, B. · 2023

Key points

  1. DreamFusion introduces Score Distillation Sampling, which uses gradients from a pretrained 2D diffusion model to optimise a 3D NeRF representation from a text prompt, without any 3D training data.
  2. It received the ICLR 2023 Outstanding Paper award and seeded the Magic3D, ProlificDreamer and DreamCraft3D lineage.
  3. DreamFusion's Score Distillation Sampling loss established the text-to-3D category and underlies a generation of asset-generation tools entering animation and game-art pipelines.

Summary

Poole et al. (2022, published ICLR 2023) present DreamFusion, the first method to generate 3D assets from text descriptions by distilling knowledge from a pretrained 2D diffusion model into a NeRF via a novel Score Distillation Sampling loss. The approach requires no 3D training data and generalises to arbitrary text prompts. Recognised as an ICLR 2023 Outstanding Paper, DreamFusion established the text-to-3D category and its Score Distillation Sampling technique directly underlies subsequent tools entering animation and game-art production pipelines.

Source

Source: ICLR 2023 ↗ (Research)

Cite this item

Poole, B., Jain, A., Barron, J. T. & Mildenhall, B. (2023). ‘DreamFusion: Text-to-3D Using 2D Diffusion’, ICLR 2023. Available at: https://arxiv.org/abs/2209.14988

Your reference manager can also read this page directly: with the Zotero (or Mendeley) browser connector installed, save it straight to your library. Whole-collection exports: RIS, BibTeX, CSL-JSON.