AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

DeformToon3D: Deformable Neural Radiance Fields for 3D Toonification

Junzhe Zhang, Yushi Lan, Shuai Yang, Fangzhou Hong, Quan Wang, Chai Kiat Yeo, Ziwei Liu, Chen Change Loy

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 22 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 instance code wR as a condition of the StyleField (ablation)DeformToon3D · Toonification, 10 stylesFID: 33.4 -> 27.6Improved
add instance code wR as a condition of the StyleField (ablation)DeformToon3D · Toonification, 10 stylesIdentity preservation: 0.735 -> 0.781Improved
use SIREN layers instead of a plain MLP for the StyleField (ablation)DeformToon3D · Toonification, 10 stylesFID: 31.8 -> 27.6Improved
add adversarial loss (ablation)DeformToon3D · Toonification, 10 stylesFID: 29.9 -> 27.6Improved
add adversarial loss (ablation)DeformToon3D · Toonification, 10 stylesIdentity preservation: 0.769 -> 0.781Improved
keep 3D generator frozen and deform with StyleField instead of fine-tuning the whole generator3D toonification (StyleSDF) · Toonification, 10 stylesIdentity preservation: 0.707 -> 0.781Improved
fine-tune both G0 and G1 rather than only the super-resolution G1CIPS-3D vs E3DGE baselines · Toonification, 10 stylesFID: 50.6 -> 34.0Improved
use a single multi-style StyleField instead of per-style fine-tuned modelsDeformToon3D · Model storage, 10 stylesstorage saving: 98.5%Improved
apply directional CLIP loss supervision to a 3D GAN (StyleGAN-NADA extension)3D GAN toonification · Toonification, 10 stylesFID: 59.3Hurt

Later papers that compared with this method

1 later accepted paper reports DeformToon3D as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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