Search papers, labs, and topics across Lattice.
The paper introduces FaithfulFaces, a framework for identity-preserving text-to-video generation (IPT2V) that addresses identity distortion issues under significant facial pose variations and occlusions. It uses a pose-shared identity aligner, which refines facial poses across different views using a pose-shared dictionary and a pose variation-identity invariance constraint. Experiments show that FaithfulFaces achieves state-of-the-art performance in maintaining identity consistency and structural clarity, even with pose changes and occlusions, validated on a newly curated high-quality video dataset with diverse facial poses.
Identity-preserving video generation just got a whole lot more faithful: FaithfulFaces maintains identity even under extreme pose variations and occlusions, a feat previous methods struggled with.
Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Despite recent progress, existing methods often suffer from significant identity distortion under large facial pose variations or facial occlusions. In this paper, we propose \textit{FaithfulFaces}, a pose-faithful facial identity preservation learning framework to improve IPT2V in complex dynamic scenes. The key of FaithfulFaces is a pose-shared identity aligner that refines and aligns facial poses across distinct views via a pose-shared dictionary and a pose variation-identity invariance constraint. By mapping single-view inputs into a global facial pose representation with explicit Euler angle embeddings, FaithfulFaces provides a pose-faithful facial prior that guides generative foundations toward robust identity-preserving generation. In particular, we develop a specialized pipeline to curate a high-quality video dataset featuring substantial facial pose diversity. Extensive experiments demonstrate that FaithfulFaces achieves state-of-the-art performance, maintaining superior identity consistency and structural clarity even as pose changes and occlusions occur.
