AI Paper Atlas

Research map / Video / Video generation

Memories are One-to-Many Mapping Alleviators in Talking Face Generation

Anni Tang, Tianyu He, Xu Tan, Jun Ling, Runnan Li, Sheng Zhao, Jiang Bian, Li Song

TPAMI 2024 · Video › Video generation · approach: Talking face generation · 27 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 implicit memory to the audio-to-expression model (ablation)audio-to-expression model · GRIDRMSE: 0.0834 -> 0.0826Improved
add implicit memory to the audio-to-expression model (ablation)audio-to-expression model · 15s HDTF adaptationRMSE: 0.1448 -> 0.1343Improved
use implicit rather than explicit memory in audio-to-expression (ablation)audio-to-expression model · GRIDRMSE: 0.0846 -> 0.0826Improved
add explicit memory to the neural-rendering model (ablation)neural-rendering model · ObamaLPIPS: 0.0248 -> 0.0207Improved
add explicit memory to the neural-rendering model (ablation)neural-rendering model · 15s HDTF adaptationLPIPS: 0.0254 -> 0.0218Improved
use explicit rather than implicit memory in neural rendering (ablation)neural-rendering model · 15s HDTF adaptationLPIPS: 0.0264 -> 0.0218Improved
increase implicit memory from 500 to 1000 key-value pairs (ablation)audio-to-expression model · GRIDRMSE: 0.0828 -> 0.0826Improved
increase implicit memory from 1000 to 2000 key-value pairs (ablation)audio-to-expression model · GRIDRMSE: 0.0826 -> 0.0825No clear effect
increase explicit memory from 100 to 300 key-value pairs (ablation)neural-rendering model · ObamaLPIPS: 0.0218 -> 0.0207Improved
increase explicit memory from 300 to 500 key-value pairs (ablation)neural-rendering model · ObamaLPIPS: 0.0207 -> 0.0205No clear effect
increase memory dimension from 64 to 128 (ablation)implicit memory · GRID vs 15s HDTF adaptationRMSE: 0.0826 -> 0.0823 on GRID; 0.1343 -> 0.1357 on HDTFMixed
use MemFace instead of ADNeRFtalking face generation · ObamaMOS overall: 3.700 -> 4.318Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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