AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

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

Ben Poole, Ajay Jain, Jonathan T. Barron, Ben Mildenhall

ICLR 2023 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 469 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Score Distillation Sampling instead of minimizing the diffusion training lossDifferentiable image parameterizations · 2D image samplingsample realismImproved
Add large ranges of viewpoints (ViewAug) (ablation)DreamFusion · Object-centric COCOgeometry qualityImproved
Add view-dependent prompts (ViewDep) (ablation)DreamFusion · Object-centric COCOgeometry qualityImproved
Add lighting to illuminated renders (ablation)DreamFusion · Object-centric COCOgeometry qualityImproved
Optimize textureless shaded geometry images (ablation)DreamFusion · Object-centric COCOgeometry qualityImproved
Add the full set of optimization choices: ViewAug, ViewDep, Lighting, and Textureless (ablation)DreamFusion · Object-centric COCOCLIP R-Precision on full renderings: +12.5%Improved
Evaluate only albedo renders instead of checking geometry with textureless renders (ablation)DreamFusion ablation evaluation · Object-centric COCOgeometry qualityHurt
Use a large classifier-free guidance weightDreamFusion · Text-to-3D synthesissample qualityImproved
Use a uniform timestep weighting instead of w(t)=σ_t²Score Distillation Sampling · Text-to-3D synthesissample qualityNo clear effect

Later papers that compared with this method

15 later accepted papers report DreamFusion as a baseline in their results tables; 15 of them report a better number on most of the results they share with it.

7 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy