HarmoView: Harmonizing Multi-View Constraints for Identity-Consistent Video Generation

• URL: http://arxiv.org/abs/2606.10839v1
• Date: Tue, 09 Jun 2026 13:26:39 GMT
• Title: HarmoView: Harmonizing Multi-View Constraints for Identity-Consistent Video Generation
• Abstract summary: 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.
• Score: 21.0568663910476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current identity-consistent video generation methods struggle to preserve appearance fidelity under large viewpoint changes. While introducing multi-view reference input offers a natural solution, progress remains constrained by the lack of effective frameworks for multi-view inputs and the scarcity of multi-view data. We address these challenges by proposing HarmoView, a robust framework for identity-consistent video generation that effectively integrates multi-view cues through three architectural refinements complemented by a staged training curriculum. Specifically, we first introduce Multi-level Feature Injection to anchor identity fidelity; by injecting raw ViT features from frontal references alongside text tokens via cross-attention, MFI provides persistent low-level appearance anchors that complement the high-level identity features within DiT blocks, leading to enhanced identity preservation. Then, we employ learnable proxy tokens to unify heterogeneous reference layouts across single-/multi-view settings while simultaneously resolving the reference-view mismatch problem. Jump-RoPE is further developed for identity-wise feature isolation to reduce identity crosstalk. To activate these structural capabilities while preserving the original generative priors, we propose the Progressive View Curriculum. This four-stage training strategy employs view dropout to facilitate a stable transition from vanilla T2V generation to high-fidelity, identity-persistent spatial reasoning. Furthermore, we construct a large-scale multi-view dataset to address the issue of data scarcity. Extensive evaluation on our multi-view benchmark, comprising 100 manually-curated cases spanning 52 unique identities, demonstrates that HarmoView significantly outperforms open-source baselines and matches leading closed-source engines, achieving state-of-the-art performance in identity-consistent video generation.

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)
• Gloria: Consistent Character Video Generation via Content Anchors [63.7455328319917]
  We propose representing character visual attributes through a compact set of anchor frames.<n>This design provides stable references for consistency, while reference-based video generation faces challenges of copy-pasting and multi-reference conflicts.<n> Experiments show our method generates high-quality character videos exceeding 10 minutes, and achieves expressive identity and appearance consistency across views, surpassing existing methods.
  arXiv  Detail & Related papers  (2026-03-31T16:06:16Z)
• AnyID: Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual References [52.81991915377852]
  We present AnyID, an ultra-fidelity identity-preservation video generation framework.<n>First, we introduce a scalable omni-referenced architecture that effectively unifies heterogeneous identity inputs into a cohesive representation.<n>Second, we propose a primary-referenced generation paradigm, which designates one reference as a canonical anchor and uses a novel differential prompt to enable precise, attribute-level controllability.
  arXiv  Detail & Related papers  (2026-03-26T08:54:48Z)
• Identity-Consistent Video Generation under Large Facial-Angle Variations [43.89758583859639]
  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.
  arXiv  Detail & Related papers  (2026-03-22T15:54:16Z)
• AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation [55.94507360511886]
  We propose AnyCrowd, a Transformer-based video generation framework capable of scaling to an arbitrary number of characters.<n>Specifically, we first introduce an Instance-Isolated Latent Representation (IILR), which encodes character instances independently prior to DiT processing to prevent latent identity entanglement.<n>Building on this disentangled representation, we further propose Tri-Stage Decoupled Attention (TSDA) to bind identities to driving poses by decomposing self-attention into: (i) instance-aware foreground attention, (ii) background-centric interaction, and (iii) global-background coordination.
  arXiv  Detail & Related papers  (2026-03-16T15:25:04Z)
• DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer [21.788582116033684]
  Video Face Swapping (VFS) requires seamlessly injecting a source identity into a target video.<n>Existing methods struggle to maintain identity similarity and attribute preservation while preserving temporal consistency.<n>We propose a comprehensive framework to seamlessly transfer the superiority of Image Face Swapping to the video domain.
  arXiv  Detail & Related papers  (2026-01-04T08:07:11Z)
• TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement [87.82338951215131]
  TokenAR is a simple but effective token-level enhancement mechanism to address reference identity confusion problem.<n>Instruct Token Injection plays as a role of extra visual feature container to inject detailed and complementary priors for reference tokens.<n>The identity-token disentanglement strategy (ITD) explicitly guides the token representations toward independently representing the features of each identity.
  arXiv  Detail & Related papers  (2025-10-18T03:36:26Z)
• 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)

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.