SEREP learns a semantic facial expression code from unpaired 3D scans and a semi-supervised image encoder, reporting lower 3D expression error than DECA, EMICA, and SMIRK on the new MultiREX benchmark.
Facial animation with disen- tangled identity and motion using transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SEREP: Semantic Facial Expression Representation for Robust In-the-Wild Capture and Retargeting
SEREP learns a semantic facial expression code from unpaired 3D scans and a semi-supervised image encoder, reporting lower 3D expression error than DECA, EMICA, and SMIRK on the new MultiREX benchmark.