atlas

Research map / Image generation / Editing and style transfer

BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation

NeurIPS 2021 · Image generation › Editing and style transfer · approach: Texture and sketch synthesis · 12 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
increase blending indicator i from 0 to 6 (fewer low-res layers receive style) (ablation)BlendGAN · AAHQ reference-guidedFID: 3.79 -> 15.08Hurt
increase blending indicator i from 0 to 6 (ablation)BlendGAN · AAHQ reference-guidedLPIPS: 0.661 -> 0.599Hurt
increase blending indicator i from 0 to 6 (ablation)BlendGAN · AAHQ latent-guidedFID: 8.97 -> 23.17Hurt
increase blending indicator i from 0 to 18 (ablation)BlendGAN · AAHQ latent-guidedLPIPS: 0.581 -> 0.159Hurt
replace raw concatenated Gram matrices (610,304-D) with self-supervised style encoder embedding (ablation)BlendGAN style code · AAHQ qualitative (reference-guided, i=0)content leakage (qualitative)Helped
one-shot finetune on out-of-distribution reference style (1000 iterations)BlendGAN · out-of-distribution stylesstyle consistency (qualitative)Helped

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