AI Paper Atlas

Research map / Video / Video generation

ReliTalk: Relightable Talking Portrait Generation from a Single Video

Haonan Qiu, Zhaoxi Chen, Yuming Jiang, Hang Zhou, Xiangyu Fan, Lei Yang, Wayne Wu, Ziwei Liu

IJCV 2024 · Video › Video generation · approach: Talking face generation · 14 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 mesh-aware guidance to audio features (ablation)ReliTalk audio-to-expression · Audio-to-expression predictionPSNR: 29.6147 -> 34.1099Improved
add phoneme audio features to mesh guidance (ablation)ReliTalk audio-to-expression · Audio-to-expression predictionPSNR: 33.8643 -> 34.1099Improved
add mesh-aware guidance when training video is short (ablation)ReliTalk · Short training video (2450 frames)PSNR: 29.5445 -> 34.8186Improved
add identity-consistent supervision with simulated lighting (ablation)ReliTalk normal estimation · Normal map qualityPSNR_grad: 21.9828 -> 23.5441Improved
add identity-consistent supervision with simulated lighting (ablation)ReliTalk normal estimation · Normal map qualitySSIM: 0.9060 -> 0.9203Improved
add identity-consistent supervision with simulated lighting (ablation)ReliTalk normal estimation · Normal map qualityPSNR: 21.7141 -> 21.5835No clear effect
add initial normal from audio-to-geometry (ablation)ReliTalk reflectance decomposition · Relighting visual resultsconvergenceImproved
add normal residual network (ablation)ReliTalk reflectance decomposition · Relighting visual resultsrelighting qualityImproved
add parsimony prior on albedo (ablation)ReliTalk reflectance decomposition · Relighting visual resultsrelighting vividnessImproved
add smoothness constraints on decomposed maps (ablation)ReliTalk reflectance decomposition · Relighting visual resultsrelighting vividnessImproved
add specular weight network (ablation)ReliTalk reflectance decomposition · Relighting visual resultssharpnessImproved
add specular map via Blinn-Phong (ablation)ReliTalk reflectance decomposition · Relighting visual resultsphotorealismImproved

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