# Identity-Consistent Video Generation under Large Facial-Angle Variations

arXiv: https://arxiv.org/abs/2603.21299 · HTML: https://mlsanity.com/paper/2603.21299/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 53 references that are in the map.
- First posted on arXiv 22 Mar 2026.

## Builds on (most cited first, 30 of 43)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [Lumiere: A Space-Time Diffusion Model for Video Generation](https://mlsanity.com/paper/2401.12945/) (2024)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [Open-Sora Plan: Open-Source Large Video Generation Model](https://mlsanity.com/paper/2412.00131/) (2024)
- [DreamVideo: Composing Your Dream Videos with Customized Subject and Motion](https://mlsanity.com/paper/2312.04433/) (2023)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [Phantom: Subject-consistent video generation via cross-modal alignment](https://mlsanity.com/paper/2502.11079/) (2025)
- [VideoBooth: Diffusion-based Video Generation with Image Prompts](https://mlsanity.com/paper/2312.00777/) (2023)
- [OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation](https://mlsanity.com/paper/2505.20292/) (2025)

## Built on by (most cited first, 3 of 3)

- [KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration](https://mlsanity.com/paper/2605.14278/) (2026)
- [PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models](https://mlsanity.com/paper/2606.26694/) (2026)
- [TexTailor: Texture-Preserving Video Virtual Try-On via Adaptive Garment Conditioning](https://mlsanity.com/paper/2609.39335/) (2026)

## Abstract (arXiv)

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 textitcopy-paste problem, particularly the textbftextitview-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 Mv2ID, 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.