AI Paper Atlas

Research map / 3D vision / Face and shape

A Multi-Implicit Neural Representation for Fonts

Pradyumna Reddy, Zhifei Zhang, Zhaowen Wang, Matthew Fisher, Hailin Jin, Niloy Mitra

NeurIPS 2021 · 3D vision › Face and shape · approach: Implicit neural representation design · 0 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 multi-implicit rendering instead of Im2Vec vector outputfont reconstruction model · Reconstruction @1024pxs-IoU: .7294 -> .9049Improved
use multi-implicit model instead of ImageVAEfont reconstruction model · Reconstruction @1024pxs-IoU: .8494 -> .9049Improved
use multi-implicit model instead of ImageVAEfont reconstruction model · Reconstruction @1024pxMSE: .0186 -> .0218Hurt
use multi-implicit model instead of Im2Vecfont reconstruction model · Reconstruction @1024pxMSE: .0571 -> .0218Improved
use multi-implicit model instead of ImageVAEfont interpolation model · Interpolation @1024pxs-IoU: .7734 -> .8234Improved
use multi-implicit model instead of ImageVAEfont interpolation model · Interpolation @1024pxMSE: .0185 -> .0343Hurt
use multi-implicit model instead of Im2Vecfont interpolation model · Interpolation @1024pxMSE: .0473 -> .0343Improved
use multi-implicit model instead of Attr2Fontfont generation model · Font generation @1024pxs-IoU: .6560 -> .8471Improved
use multi-implicit model instead of Attr2Fontfont generation model · Font generation @1024pxMSE: .2563 -> .1083Improved
use multi-implicit model instead of DeepSVGfont generation model · Font generation @128pxs-IoU: .3584 -> .8429Improved
increase test resolution from 128 to 1024 for ImageVAE (bilinear upsampling)ImageVAE · ReconstructionMSE: .0072 -> .0186Hurt
increase test resolution from 128 to 1024 for multi-implicit modelmulti-implicit model · Reconstructions-IoU: .8750 -> .9049Improved

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