AI Paper Atlas

Research map / 3D vision / 3D generation

Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation

Fangfu Liu, Hanyang Wang, Weiliang Chen, Haowen Sun, Yueqi Duan

ECCV 2024 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 27 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
add identity-aware optimization of the 2D personalized model (ablation)Make-Your-3D · Qualitative ablation (Fig.)subject preservation and consistencyImproved
add subject-prior optimization of the multi-view diffusion model (ablation)Make-Your-3D · Qualitative ablation (Fig.)multi-view rendering plausibilityImproved
use single-image feed-forward-style adapter pipeline instead of DreamBooth3D NeRF fine-tuningsubject-driven 3D generation · Generation timetime per subject: 3 hours -> 5 minutes (36x faster)Improved
Make-Your-3D versus multi-view DreamBooth baselinesubject-driven 3D generation · DreamBooth3D dataset rendersCLIP R-Precision (ViT-B/32): 0.735 -> 0.764Improved

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