Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

WildActor: Unconstrained Identity-Preserving Video Generation

Qin Guo, Tianyu Yang, Xuanhua He, Fei Shen, Yong Zhang, Zhuoliang Kang, Xiaoming Wei, Dan Xu

TL;DR

This work presents Actor-18M, a large-scale human video dataset designed to capture identity consistency under unconstrained viewpoints and environments, and proposes WildActor, a framework for any-view conditioned human video generation.

Abstract

Production-ready human video generation requires digital actors to maintain strictly consistent full-body identities across dynamic shots, viewpoints and motions, a setting that remains challenging for existing methods. Prior methods often suffer from face-centric behavior that neglects body-level consistency, or produce copy-paste artifacts where subjects appear rigid due to pose locking. We present Actor-18M, a large-scale human video dataset designed to capture identity consistency under unconstrained viewpoints and environments. Actor-18M comprises 1.6M videos with 18M corresponding human images, covering both arbitrary views and canonical three-view representations. Leveraging Actor-18M, we propose WildActor, a framework for any-view conditioned human video generation. We introduce an Asymmetric Identity-Preserving Attention mechanism coupled with a Viewpoint-Adaptive Monte Carlo Sampling strategy that iteratively re-weights reference conditions by marginal utility for balanced manifold coverage. Evaluated on the proposed Actor-Bench, WildActor consistently preserves body identity under diverse shot compositions, large viewpoint transitions, and substantial motions, surpassing existing methods in these challenging settings.

WildActor: Unconstrained Identity-Preserving Video Generation

TL;DR

This work presents Actor-18M, a large-scale human video dataset designed to capture identity consistency under unconstrained viewpoints and environments, and proposes WildActor, a framework for any-view conditioned human video generation.

Abstract

Production-ready human video generation requires digital actors to maintain strictly consistent full-body identities across dynamic shots, viewpoints and motions, a setting that remains challenging for existing methods. Prior methods often suffer from face-centric behavior that neglects body-level consistency, or produce copy-paste artifacts where subjects appear rigid due to pose locking. We present Actor-18M, a large-scale human video dataset designed to capture identity consistency under unconstrained viewpoints and environments. Actor-18M comprises 1.6M videos with 18M corresponding human images, covering both arbitrary views and canonical three-view representations. Leveraging Actor-18M, we propose WildActor, a framework for any-view conditioned human video generation. We introduce an Asymmetric Identity-Preserving Attention mechanism coupled with a Viewpoint-Adaptive Monte Carlo Sampling strategy that iteratively re-weights reference conditions by marginal utility for balanced manifold coverage. Evaluated on the proposed Actor-Bench, WildActor consistently preserves body identity under diverse shot compositions, large viewpoint transitions, and substantial motions, surpassing existing methods in these challenging settings.
Paper Structure (24 sections, 6 equations, 4 figures, 4 tables)

This paper contains 24 sections, 6 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. The Proposed Actor-18M Dataset
  4. Data Collection and Filtering
  5. Data Construction
  6. Data Statistics
  7. The Proposed Method
  8. Preliminaries
  9. Model Design
  10. Training Scheme
  11. Experiments
  12. Implementation Details
  13. The Proposed Actor-Bench
  14. Evaluation
  15. Ablation Study
  16. ...and 9 more sections

Figures (4)

  • Figure 1: Construction pipeline and representative samples of Actor-18M.Left: Frames are sampled and filtered from identity-consistent videos, from which facial and body images are extracted as ground-truth references. Right: Based on these references, view-transformed samples are generated to construct Actor-18M-A, while attribute-conditioned image editing under diverse environments, lighting conditions, and motions produces Actor-18M-B. Canonical three-view images in Actor-18M-C are generated using Nano-Banana, guided by frames with the highest visibility selected from different viewpoints, serving as complete identity anchors.
  • Figure 2: Overview of WildActor.Left: The overall architecture, where a video DiT is conditioned on multi-view facial and body reference images selected via Viewpoint-Adaptive Monte Carlo Sampling. Reference tokens are embedded with I-RoPE to distinguish them from video tokens in the shared spatio-temporal attention space. Right: Details of AIPA, illustrating how identity reference tokens are aggregated and injected into video tokens through asymmetric attention while preserving prior of backbone.
  • Figure 3: Qualitative comparison on sequential narrative.WildActor maintains stronger full-body consistency and prompt adherence than prior methods under viewpoint changes, camera motion, and scene transitions. Zoom in to better compare fine-grained details.
  • Figure 5: Ablation study on data strategies and model components. We evaluate variants in controlled scenes with turning motions, enabling clear comparison under viewpoint changes.