AI Paper Atlas

Research map / Image generation / Editing and style transfer

PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering

Yurui Ren, Ge Li, Yuanqi Chen, Thomas H. Li, Shan Liu

ICCV 2021 · Image generation › Editing and style transfer · approach: Talking face generation · 228 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 a window of continuous frames of 3DMM coefficients instead of a single frame as motion descriptor (ablation)PIRenderer · Same-identity reconstructionFID: 8.752 -> 8.260Improved
use a window of continuous frames of 3DMM coefficients instead of a single frame as motion descriptor (ablation)PIRenderer · Same-identity reconstructionAED: 0.1169 -> 0.1106Improved
use a window of continuous frames of 3DMM coefficients instead of a single frame as motion descriptor (ablation)PIRenderer · Same-identity reconstructionLPIPS: 0.1370 -> 0.1285Improved
use a window of continuous frames of 3DMM coefficients instead of a single frame as motion descriptor (ablation)PIRenderer · Same-identity reconstructionAPD: 0.0182 -> 0.0164Improved
use fully disentangled 3DMM motion descriptor instead of keypoints (FOMM)PIRenderer · Cross-identity motion imitationFID: 38.92 -> 28.18Improved
use fully disentangled 3DMM motion descriptor instead of landmarks (GFLA)PIRenderer · Cross-identity motion imitationAED: 0.2599 -> 0.2304Improved
use PIRenderer instead of FOMMPIRenderer · Same-identity reconstructionLPIPS: 0.1220 -> 0.1285Hurt
use PIRenderer instead of StyleRig (StyleGAN generator)PIRenderer · Portrait editing (StyleGAN images)FID: 47.37 -> 65.97Hurt
use PIRenderer instead of StyleRigPIRenderer · Portrait editing (StyleGAN images)AED: 0.316 -> 0.257Improved
use PIRenderer instead of StyleRigPIRenderer · Portrait editing (StyleGAN images)APD: 0.0919 -> 0.0252Improved
use PIRenderer instead of FOMMPIRenderer · Cross-identity motion imitationJND fooling rate: 19.4% -> 25.5%Improved

Later papers that compared with this method

1 later accepted paper reports PIRenderer as a baseline in their results tables; 0 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