AI Paper Atlas

Research map / Video / Video generation

LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces From Video Using Pose and Lighting Normalization

Avisek Lahiri, Vivek Kwatra, Christian Frueh, John Lewis, Chris Bregler

CVPR 2021 · Video › Video generation · approach: Talking face generation · 100 citations (OpenAlex)

Check 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 audio latent length 256 instead of 32 (ablation)LipSync3D · Speakers A and B (average)LMD: 3.023 -> 1.810Improved
Use audio latent length 256 instead of 64 (ablation)LipSync3D · Speakers A and B (average)LMD: 2.783 -> 1.810Improved
Use audio latent length 256 instead of 128 (ablation)LipSync3D · Speakers A and B (average)LMD: 2.598 -> 1.810Improved
Use audio latent length 512 instead of 256 (ablation)LipSync3D · Speakers A and B (average)LMD: 1.810 -> 2.765Hurt
Use audio latent length 1024 instead of 256 (ablation)LipSync3D · Speakers A and B (average)LMD: 1.810 -> 2.987Hurt

Later papers that compared with this method

1 later accepted paper reports LipSync3D as a baseline in their results tables; 1 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