AI Paper Atlas

Research map / 3D vision / Face and shape

Cross-Modal 3D Shape Generation and Manipulation

Zezhou Cheng, Menglei Chai, Jian Ren, Hsin-Ying Lee, Kyle Olszewski, Zeng Huang, Subhransu Maji, Sergey Tulyakov

ECCV 2022 · 3D vision › Face and shape · approach: 3D shape generative modeling · 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 multi-trial latent optimization (pick lowest-loss code) (ablation)MM-VADs single-view sketch reconstruction · ShapeNet airplanesmean Chamfer distance: 5.50 -> 1.73Improved
add multi-trial latent optimization (pick lowest-loss code) (ablation)MM-VADs single-view sketch reconstruction · ShapeNet chairsmean Chamfer distance: 9.10 -> 4.70Improved
add latent regularization loss gamma*max(||z||^2,beta) (ablation)MM-VADs single-view reconstruction · ShapeNet single-view reconstructionreconstruction successImproved
use 128-dim instead of 32-dim latent codes (ablation)MM-VADs · ShapeNet shape reconstructionshape reconstruction qualityImproved
replace task-specific encoder-decoder with MM-VADs latent optimization under 1/2-horizontal occlusionsingle-view reconstruction · ShapeNet, 1/2-horizontal inputavg Chamfer distance x1e3: 8.36 -> 3.56Improved
replace encoder-decoder with MM-VADs under 1/4-vertical occlusionsingle-view reconstruction · ShapeNet, 1/4-vertical inputavg Chamfer distance x1e3: 11.61 -> 5.60Improved
replace encoder-decoder with MM-VADs on full-view inputsingle-view reconstruction · ShapeNet, Full inputavg Chamfer distance x1e3: 2.59 -> 3.44Hurt
apply few-shot adaptation with 10 2D images (MineGAN-style mapping)MM-VADs · Few-shot generation (avg)classification error: 0.75 -> 0.04Improved
apply few-shot adaptation with 10 2D imagesMM-VADs · Few-shot generation (avg)FID: 109.0 -> 105.3Improved
edit color with scribbles via latent optimizationMM-VADs · Color editing, airplanePSNR: 19.84 -> 26.41Improved
edit color with scribbles via latent optimizationMM-VADs · Color editing, chairLPIPS: 0.33 -> 0.20Improved
sketch edit removing airplane engineMM-VADs · Sketch shape editing, airplane - engineChamfer distance to manual edit: 0.096 -> 0.059Improved

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