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

February 09, 2026

Reading time: 1 minute

...

📝 Original Info

Title: Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding
ArXiv ID: 2601.01352
Date: 2026-01-04
Authors: Yixuan Lai, He Wang, Kun Zhou, Tianjia Shao

📝 Abstract

Producing prompt-faithful videos that preserve a userspecified 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 poselocked 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 backbonecompatible. 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.

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)

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

📝 Original Info

📝 Abstract

📄 Full Content

Table of Contents

Table of Contents

📝 Original Info

📝 Abstract

📄 Full Content

Start searching

No results found