AI Paper Atlas

Research map / Image generation / Editing and style transfer

Neural Transformation Fields for Arbitrary-Styled Font Generation

Bin Fu, Junjun He, Jianjun Wang, Yu Qiao

CVPR 2023 · Image generation › Editing and style transfer · approach: Texture and sketch synthesis · 21 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 localized rather than universal style representation (ablation)NTF · Unseen Fonts and Seen ContentsSSIM: 0.6102 -> 0.6299Improved
use localized rather than universal style representation (ablation)NTF · Unseen Fonts and Unseen ContentsSSIM: 0.6331 -> 0.6533Improved
use localized rather than universal style representation (ablation)NTF · Unseen Fonts and Seen ContentsFID: 30.46 -> 13.72Improved
use localized rather than universal style representation (ablation)NTF · Unseen Fonts and Unseen ContentsFID: 33.12 -> 15.67Improved
add NTF-based transformation and rendering instead of the base generation process (ablation)Font generation · Unseen Fonts and Seen ContentsSSIM: 0.6189 -> 0.6229Improved
use 10 rather than 5 sampling points (ablation)NTF font rendering · Unseen Fonts and Seen ContentsSSIM: 0.6229 -> 0.6280Improved
use 15 rather than 10 sampling points (ablation)NTF font rendering · Unseen Fonts and Seen ContentsSSIM: 0.6280 -> 0.6299Improved
increase sampling points from 15 to 20 (ablation)NTF font rendering · Unseen Fonts and Seen ContentsSSIM: 0.6299 -> 0.6260Hurt
add NTF-based transformation and rendering instead of the base generation process (ablation)Font generation · Unseen Fonts and Unseen ContentsSSIM: 0.6413 -> 0.6466Improved
use 10 rather than 5 sampling points (ablation)NTF font rendering · Unseen Fonts and Unseen ContentsSSIM: 0.6466 -> 0.6503Improved
use 15 rather than 10 sampling points (ablation)NTF font rendering · Unseen Fonts and Unseen ContentsSSIM: 0.6503 -> 0.6533Improved
increase sampling points from 15 to 20 (ablation)NTF font rendering · Unseen Fonts and Unseen ContentsSSIM: 0.6533 -> 0.6473Hurt

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