AI Paper Atlas

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

DreamBooth3D: Subject-Driven Text-to-3D Generation

Amit Raj, Srinivas Kaza, Ben Poole, Michael Niemeyer, Nataniel Ruiz, Ben Mildenhall, Shiran Zada, Kfir Aberman, Michael Rubinstein, Jonathan Barron, Yuanzhen Li, Varun Jampani

ICCV 2023 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 236 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 3-stage optimization (partial DreamBooth NeRF, pseudo multi-view data, multi-view DreamBooth NeRF) instead of naive DreamBooth followed by DreamFusionDreamBooth3D · DreamBooth dataset, CLIP R-PrecisionCLIP R-Precision ViT-B/16: 0.509 -> 0.783Improved
use 3-stage optimization instead of naive DreamBooth+FusionDreamBooth3D · DreamBooth dataset, CLIP R-PrecisionCLIP R-Precision ViT-L-14: 0.506 -> 0.797Improved
fully finetune DreamBooth before DreamFusion (naive DreamBooth+Fusion) (ablation)DreamBooth+Fusion · DreamBooth dataset, qualitative3D consistency (Janus problem)Hurt
use partially finetuned DreamBooth (150 iterations) for the initial NeRF (ablation)DreamBooth3D stage 1 · DreamBooth dataset, qualitative3D coherenceImproved
run stage 3 (multi-view DreamBooth plus final NeRF) after the initial NeRF (ablation)DreamBooth3D · DreamBooth dataset, qualitativesubject likenessImproved
add weak reconstruction loss on pseudo multi-view images in final NeRF (ablation)DreamBooth3D stage 3 · DreamBooth dataset, qualitativecolor fidelityImproved
DreamBooth3D versus DreamBooth+Fusion and Latent-NeRF in pairwise user studyDreamBooth3D · DreamBooth dataset user studypreference on 3D consistency, subject fidelity, prompt fidelityImproved

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