Identity-Consistent Video Generation under Large Facial-Angle Variations

• URL: http://arxiv.org/abs/2603.21299v1
• Date: Sun, 22 Mar 2026 15:54:16 GMT
• Title: Identity-Consistent Video Generation under Large Facial-Angle Variations
• Abstract summary: Single-view reference-to-video methods often struggle to preserve identity consistency under large facial-angle variations.<n>We propose $mathrmMv2mathrmID$, a multi-view conditioned framework under in-paired supervision.<n>Our method significantly improves identity consistency while maintaining motion naturalness, outperforming existing approaches trained with cross-paired data.
• Score: 43.89758583859639
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Single-view reference-to-video methods often struggle to preserve identity consistency under large facial-angle variations. This limitation naturally motivates the incorporation of multi-view facial references. However, simply introducing additional reference images exacerbates the \textit{copy-paste} problem, particularly the \textbf{\textit{view-dependent copy-paste}} artifact, which reduces facial motion naturalness. Although cross-paired data can alleviate this issue, collecting such data is costly. To balance the consistency and naturalness, we propose $\mathrm{Mv}^2\mathrm{ID}$, a multi-view conditioned framework under in-paired supervision. We introduce a region-masking training strategy to prevent shortcut learning and extract essential identity features by encouraging the model to aggregate complementary identity cues across views. In addition, we design a reference decoupled-RoPE mechanism that assigns distinct positional encoding to video and conditioning tokens for better modeling of their heterogeneous properties. Furthermore, we construct a large-scale dataset with diverse facial-angle variations and propose dedicated evaluation metrics for identity consistency and motion naturalness. Extensive experiments demonstrate that our method significantly improves identity consistency while maintaining motion naturalness, outperforming existing approaches trained with cross-paired data.

Related papers

• GroupVideo: Multi-Identity Customized Text-to-Video Generation [53.89036635198158]
  GroupVideo is a novel framework that leverages multiple individual photographs to generate identitycustomized video.<n>GroupVideo incorporates multimodal identity alignment, while semantic alignment introduces a semantic perceiver to enhance the naturalness of motions.<n>In response to the shortage of multi-ID video datasets, we have curated a comprehensive high-quality dataset of 20,000 videos.
  arXiv  Detail & Related papers  (2026-07-23T08:09:04Z)
• HarmoView: Harmonizing Multi-View Constraints for Identity-Consistent Video Generation [21.0568663910476]
  HarmoView is a robust framework for identity-consistent video generation.<n>It integrates multi-view cues through three architectural refinements and a staged training curriculum.<n>HarmoView significantly outperforms open-source baselines and matches leading closed-source engines.
  arXiv  Detail & Related papers  (2026-06-09T13:26:39Z)
• Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement [54.199726425201895]
  Multimodal editing large models have demonstrated powerful editing capabilities across diverse tasks.<n>Current facial ID preservation methods struggle to achieve consistent restoration of both facial identity and edited element IP.<n>We propose EditedID, an Alignment-Disentanglement-Entanglement framework for robust identity-specific facial restoration.
  arXiv  Detail & Related papers  (2026-02-21T08:24:42Z)
• Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization [55.29071072675132]
  Face anonymization aims to conceal identity information while preserving non-identity attributes.<n>We propose textbfIDsuperscript2Face, a training-centric anonymization framework.<n>We show that IDtextsuperscript2Face outperforms existing methods in visual quality, identity suppression, and utility preservation.
  arXiv  Detail & Related papers  (2025-10-28T09:28:12Z)
• WithAnyone: Towards Controllable and ID Consistent Image Generation [83.55786496542062]
  Identity-consistent generation has become an important focus in text-to-image research.<n>We develop a large-scale paired dataset tailored for multi-person scenarios.<n>We propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity.
  arXiv  Detail & Related papers  (2025-10-16T17:59:54Z)
• From Large Angles to Consistent Faces: Identity-Preserving Video Generation via Mixture of Facial Experts [69.44297222099175]
  We introduce a Mixture of Facial Experts (MoFE) that captures distinct but mutually reinforcing aspects of facial attributes.<n>To mitigate dataset limitations, we have tailored a data processing pipeline centered on two key aspects: Face Constraints and Identity Consistency.<n>We have curated and refined a Large Face Angles (LFA) dataset from existing open-source human video datasets.
  arXiv  Detail & Related papers  (2025-08-13T04:10:16Z)
• Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration [9.481604837168762]
  Face Video Restoration (FVR) aims to recover high-quality face videos from degraded versions.<n>Traditional methods struggle to preserve fine-grained, identity-specific features when degradation is severe.<n>We introduce IP-FVR, a novel method that leverages a high-quality reference face image as a visual prompt to provide identity conditioning during the denoising process.
  arXiv  Detail & Related papers  (2025-07-14T14:01:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.