AI Paper Atlas

Research map / 3D vision / Face and shape

Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation

Taekyung Ki, Dongchan Min, Gyeongsu Chae

ECCV 2024 · 3D vision › Face and shape · approach: Speech-driven 3D facial animation · 7 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 contrastive pre-training (CLeBS) instead of raw 3DMM expression injection (ablation)Export3D · VFHQ cross-identityCSIM: 0.648 -> 0.694Improved
add contrastive pre-training instead of end-to-end LeBS (n=10) (ablation)Export3D · VFHQ same-identityAED: 0.110 -> 0.082Improved
reduce number of basis vectors n in end-to-end LeBS from 25 to 5 (ablation)E2E LeBS · VFHQ same-identityCSIM: 0.745 -> 0.658Hurt
use EAdaLN instead of cross-attention for expression conditioning (ablation)Export3D generator · VFHQ same-identityCSIM: 0.678 -> 0.811Improved
use EAdaLN instead of cross-attention (ablation)Export3D generator · VFHQ cross-identityAED: 0.271 -> 0.208Improved
Export3D vs HiDe-NeRF identity preservationExport3D · VFHQ same-identityCSIM: 0.867 -> 0.811Hurt
Export3D vs DPE on structural similarityExport3D · VFHQ same-identitySSIM: 0.750 -> 0.704Hurt
Gaussian low-pass filter after pixel shuffle upsamplingtri-plane generator · qualitativegrid artifactsImproved

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