Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding

• URL: http://arxiv.org/abs/2601.01352v1
• Date: Sun, 04 Jan 2026 03:41:55 GMT
• Title: Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding
• Authors: Yixuan Lai, He Wang, Kun Zhou, Tianjia Shao,
• Abstract summary: We present an identity-conditioned variant of a diffusion-transformer video generator.<n>A short clip reveals subject-specific patterns, e.g., how smiles form, across poses and lighting.<n>The approach consistently improves identity retention under large pose changes and expressive facial behavior.
• Score: 30.62635724018122
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Producing prompt-faithful videos that preserve a user-specified identity remains challenging: models need to extrapolate facial dynamics from sparse reference while balancing the tension between identity preservation and motion naturalness. Conditioning on a single image completely ignores the temporal signature, which leads to pose-locked motions, unnatural warping, and "average" faces when viewpoints and expressions change. To this end, we introduce an identity-conditioned variant of a diffusion-transformer video generator which uses a short reference video rather than a single portrait. Our key idea is to incorporate the dynamics in the reference. A short clip reveals subject-specific patterns, e.g., how smiles form, across poses and lighting. From this clip, a Sinkhorn-routed encoder learns compact identity tokens that capture characteristic dynamics while remaining pretrained backbone-compatible. Despite adding only lightweight conditioning, the approach consistently improves identity retention under large pose changes and expressive facial behavior, while maintaining prompt faithfulness and visual realism across diverse subjects and prompts.

Related papers

• AlcheMinT: Fine-grained Temporal Control for Multi-Reference Consistent Video Generation [58.844504598618094]
  We propose AlcheMinT, a unified framework that introduces explicit timestamps conditioning for subject-driven video generation.<n>Our approach introduces a novel positional encoding mechanism that unlocks the encoding of temporal intervals, associated in our case with subject identities.<n>We incorporate subject-descriptive text tokens to strengthen binding between visual identity and video captions, mitigating ambiguity during generation.
  arXiv  Detail & Related papers  (2025-12-11T18:59:34Z)
• DirectSwap: Mask-Free Cross-Identity Training and Benchmarking for Expression-Consistent Video Head Swapping [58.2549561389375]
  Video head swapping aims to replace the entire head of a video subject, including facial identity, head shape, and hairstyle, with that of a reference image.<n>Due to the lack of ground-truth paired swapping data, prior methods typically train on cross-frame pairs of the same person within a video.<n>We propose DirectSwap, a mask-free, direct video head-swapping framework that extends an image U-Net into a video diffusion model.
  arXiv  Detail & Related papers  (2025-12-10T08:31:28Z)
• Mask-Free Audio-driven Talking Face Generation for Enhanced Visual Quality and Identity Preservation [54.52905471078152]
  We propose a mask-free talking face generation approach while maintaining the 2D-based face editing task.<n>We transform the input images to have closed mouths, using a two-step landmark-based approach trained in an unpaired manner.
  arXiv  Detail & Related papers  (2025-07-28T16:03:36Z)
• CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulation [39.665632874158426]
  CanonSwap is a video face-swapping framework that decouples motion information from appearance information.<n>Our method significantly outperforms existing approaches in terms of visual quality, temporal consistency, and identity preservation.
  arXiv  Detail & Related papers  (2025-07-03T15:03:39Z)
• Proteus-ID: ID-Consistent and Motion-Coherent Video Customization [17.792780924370103]
  Video identity customization seeks to synthesize realistic, temporally coherent videos of a specific subject, given a single reference image and a text prompt.<n>This task presents two core challenges: maintaining identity consistency while aligning with the described appearance and actions, and generating natural, fluid motion without unrealistic stiffness.<n>We introduce Proteus-ID, a novel diffusion-based framework for identity-consistent and motion-coherent video customization.
  arXiv  Detail & Related papers  (2025-06-30T11:05:32Z)
• VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention [76.3175166538482]
  VideoGen-of-Thought (VGoT) is a step-by-step framework that automates multi-shot video synthesis from a single sentence.<n>VGoT addresses three core challenges: Narrative fragmentation, visual inconsistency, and transition artifacts.<n>Combined in a training-free pipeline, VGoT surpasses strong baselines by 20.4% in within-shot face consistency and 17.4% in style consistency.
  arXiv  Detail & Related papers  (2024-12-03T08:33:50Z)
• PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation [36.21554597804604]
  Identity-specific human video generation with customized ID images is still under-explored.<n>Key challenge lies in maintaining high ID fidelity consistently while preserving the original motion dynamic and semantic following.<n>We propose a novel framework, dubbed $textbfPersonalVideo$, that applies a mixture of reward supervision on synthesized videos.
  arXiv  Detail & Related papers  (2024-11-26T02:25:38Z)
• VividPose: Advancing Stable Video Diffusion for Realistic Human Image Animation [79.99551055245071]
  We propose VividPose, an end-to-end pipeline that ensures superior temporal stability. An identity-aware appearance controller integrates additional facial information without compromising other appearance details. A geometry-aware pose controller utilizes both dense rendering maps from SMPL-X and sparse skeleton maps. VividPose exhibits superior generalization capabilities on our proposed in-the-wild dataset.
  arXiv  Detail & Related papers  (2024-05-28T13:18:32Z)
• When StyleGAN Meets Stable Diffusion: a $\mathscr{W}_+$ Adapter for Personalized Image Generation [60.305112612629465]
  Text-to-image diffusion models have excelled in producing diverse, high-quality, and photo-realistic images. We present a novel use of the extended StyleGAN embedding space $mathcalW_+$ to achieve enhanced identity preservation and disentanglement for diffusion models. Our method adeptly generates personalized text-to-image outputs that are not only compatible with prompt descriptions but also amenable to common StyleGAN editing directions.
  arXiv  Detail & Related papers  (2023-11-29T09:05:14Z)
• Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose [23.211318473026243]
  We propose a self-supervised hybrid model (DAE-GAN) that learns how to reenact face naturally given large amounts of unlabeled videos. Our approach combines two deforming autoencoders with the latest advances in the conditional generation. Experiment results demonstrate the superior quality of reenacted images and the flexibility of transferring facial movements between identities.
  arXiv  Detail & Related papers  (2020-03-29T06:45:17Z)

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.