AI Paper Atlas

Research map / 3D vision / Face and shape

PINA: Learning a Personalized Implicit Neural Avatar From a Single RGB-D Video Sequence

Zijian Dong, Chen Guo, Jie Song, Xu Chen, Andreas Geiger, Otmar Hilliges

CVPR 2022 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 62 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 PINA's joint canonical-space sequence fusion instead of framewise reconstructionHuman reconstruction on BUFF · BUFFIoU: 0.783 -> 0 . 8 7 9Improved
Use PINA's joint canonical-space sequence fusion instead of framewise reconstructionHuman reconstruction on BUFF · BUFFChamfer distance (cm): 2.1 -> 1.1Improved
Use PINA's joint canonical-space sequence fusion instead of framewise reconstructionHuman reconstruction on BUFF · BUFFNormal consistency: 0.861 -> 0 . 9 2 7Improved
Use PINA with partial 2.5D input instead of SCANimate (2.5D)Animation · CAPEIoU: 0.665 -> 0.946Improved
Use PINA with partial 2.5D input instead of SCANimate (2.5D)Animation · CAPEChamfer distance (cm): 3.704 -> 0.666Improved
Use PINA with partial 2.5D input instead of SCANimate (2.5D)Animation · CAPENormal consistency: 0.785 -> 0.906Improved
Disable joint pose optimization (ablation)PINA · BUFFIoU: 0.879 -> 0.850Hurt
Disable joint pose optimization (ablation)PINA · BUFFChamfer distance (cm): 1.1 -> 1.6Hurt
Disable joint pose optimization (ablation)PINA · BUFFNormal consistency: 0 . 9 2 7 -> 0.887Hurt
Remove pose conditioning from the shape network (ablation)PINA · CAPEChamfer distance (cm): 0.604 -> 0.991Hurt
Replace learned skinning weights with SMPL weights (ablation)PINA · CAPENormal consistency: 0.912 -> 0.887Hurt

Later papers that compared with this method

2 later accepted papers report PINA as a baseline in their results tables; 2 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