AI Paper Atlas

Research map / 3D vision / Face and shape

3DStyleNet: Creating 3D Shapes With Geometric and Texture Style Variations

Kangxue Yin, Jun Gao, Maria Shugrina, Sameh Khamis, Sanja Fidler

ICCV 2021 · 3D vision › Face and shape · approach: Textured mesh generation · 71 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 3DStyleNet geometry and texture augmentation versus no augmentationDISN · 3D reconstruction, animals, Unseen ShapesChamfer distance: 0.065 -> 0.037Improved
add random affine augmentationDISN · 3D reconstruction, animals, Seen ShapesChamfer distance: 0.025 -> 0.040Hurt
add joint test-time fine-tuning of geometry and texture networks (ablation)3DStyleNet · 3D reconstruction, animals, Unseen ShapesChamfer distance: 0.039 -> 0.037Improved
add joint test-time fine-tuning of geometry and texture networks (ablation)3DStyleNet · 3D reconstruction, animals, Unseen ShapesF-score: 0.183 -> 0.218Improved
add texture transfer to geometry transfer only (ablation)3DStyleNet · 3D reconstruction, animals, Unseen ShapesChamfer distance: 0.040 -> 0.037Improved
add geometry transfer to texture transfer only (ablation)3DStyleNet · 3D reconstruction, animals, Unseen ShapesChamfer distance: 0.051 -> 0.037Improved
add geometry transfer to texture transfer only (ablation)3DStyleNet · 3D reconstruction, animals, Seen ShapesChamfer distance: 0.012 -> 0.016Hurt
use part-aware affine geometry transfer instead of Neural Cage geometryDISN · 3D reconstruction, animals, Unseen ShapesChamfer distance: 0.044 -> 0.040Improved
use 3DStyleNet full instead of random COCO texture augmentationDISN · 3D reconstruction, animals, Unseen ShapesChamfer distance: 0.045 -> 0.037Improved
use 3DStyleNet full instead of Neural Cage + Style TransferDISN · 3D reconstruction, animals, Unseen ShapesF-score: 0.181 -> 0.218Improved
use 3DStyleNet versus Neural Cage + Style Transfer on ChamferDISN · 3D reconstruction, animals, Unseen ShapesChamfer distance: 0.040 -> 0.037Improved
use 3DStyleNet instead of Neural Cage plus style transfer in user study3DStyleNet · AMT user studyusers closer to target: 41.9% vs 26.8%Improved

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