AI Paper Atlas

Research map / 3D vision / Face and shape

DreamStone: Image as a Stepping Stone for Text-Guided 3D Shape Generation

Zhengzhe Liu, Peng Dai, Ruihui Li, Xiaojuan Qi, Chi‐Wing Fu

TPAMI 2023 · 3D vision › Face and shape · approach: 3D shape generative modeling · 17 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 stage-1 image-to-shape alignment (ablation)DreamStone · ShapeNet text-to-shapeFID: 222.96 -> 114.34Improved
add stage-1 image-to-shape alignment (ablation)DreamStone · ShapeNet text-to-shapeConsistency Score (%): 1.92 -> 70.77Improved
add stage-2 text-to-shape alignment (ablation)DreamStone · ShapeNet text-to-shapeFID: 202.33 -> 114.34Improved
add stage-2 text-to-shape alignment (ablation)DreamStone · ShapeNet text-to-shapeConsistency Score (%): 29.52 -> 70.77Improved
add background loss in stage 1 (ablation)DreamStone · ShapeNet text-to-shapeFID: 149.45 -> 114.34Improved
add background loss in stage 2 (ablation)DreamStone · ShapeNet text-to-shapeFID: 156.52 -> 114.34Improved
add background loss in both stages (ablation)DreamStone · ShapeNet text-to-shapeFID: 178.34 -> 114.34Improved
add background loss in both stages (ablation)DreamStone · ShapeNet text-to-shapeConsistency Score (%): 30.96 -> 70.77Improved
map CLIP image feature to SVR shape space instead of decoding from CLIP image encoder (ablation)DVR decoder · ShapeNet text-to-shapeFID: 181.88 -> 114.34Improved
use mapped two-stage alignment instead of text-to-image then DVR (LAFITE+DVR)DreamStone · ShapeNet text-to-shapeFID: 135.01 -> 114.34Improved
add diffusion prior and SDS refinement to ISSISS · ShapeNet text-to-shapeFID: 124.42 -> 114.34Improved
add diffusion prior and SDS refinement to ISSISS · ShapeNet text-to-shapeConsistency Score (%): 60.0 -> 70.77Improved

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