AI Paper Atlas

Research map / 3D vision / Face and shape

OTAvatar: One-Shot Talking Face Avatar With Controllable Tri-Plane Rendering

Zhiyuan Ma, Xiangyu Zhu, Guo-Jun Qi, Zhen Lei, Lei Zhang

CVPR 2023 · 3D vision › Face and shape · approach: Speech-driven 3D facial animation · 57 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 decoupling-by-inverting rather than joint training (ablation)OTAvatar · HDTF cross-identity reenactmentCSIM: 0.689 -> 0.694Improved
Use decoupling-by-inverting rather than joint training (ablation)OTAvatar · HDTF cross-identity reenactmentAED: 3.009 -> 2.850Improved
Add landmark-region loss (ablation)OTAvatar · HDTF cross-identity reenactmentAED: 3.101 -> 2.850Improved
Add ID loss (ablation)OTAvatar · HDTF cross-identity reenactmentCSIM: 0.592 -> 0.694Improved
Add ID loss (ablation)OTAvatar · HDTF cross-identity reenactmentAED: 3.164 -> 2.850Improved
Fine-tune the EG3D generator after controller training (ablation)OTAvatar · HDTF cross-identity reenactmentCSIM: 0.687 -> 0.694Improved
Fine-tune the EG3D generator after controller training (ablation)OTAvatar · HDTF cross-identity reenactmentAED: 3.145 -> 2.850Improved
Use separate latent motion codes instead of one W-space code repeated across slots (ablation)OTAvatar · HDTF cross-identity reenactmentAED: 3.352 -> 2.850Improved
Use separate latent motion codes instead of one W-space code repeated across slots (ablation)OTAvatar · HDTF cross-identity reenactmentCSIM: 0.719 -> 0.694Mixed
Use a learnable orthogonal codebook instead of vanilla linear weights (ablation)OTAvatar controller · HDTF cross-identity reenactmentAED, APD, AKD, FIDImproved
Set identity optimization/controller training steps to 90/10 rather than other tested splits (ablation)OTAvatar · HDTF cross-identity reenactmentAED and CSIM: 3.285 / 0.7200; 3.178 / 0.716; 2.850 / 0.694; 3.231 / 0.592Mixed

Later papers that compared with this method

1 later accepted paper reports OTAvatar as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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