Papers
arxiv:2605.10079

SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation

Published on May 11
Authors:
,
,
,
,

Abstract

SocialDirector is a training-free controller that improves multi-person video generation by guiding cross-attention to match actors with actions and direct them toward intended targets.

Video generation has advanced rapidly, producing photorealistic videos from text or image prompts. Meanwhile, film production and social robotics increasingly demand multi-person videos with rich social interactions, including conversations, gestures, and coordinated actions. However, existing models offer no explicit control over interactions, such as who performs which action, when it occurs, and toward whom it is directed. This often results in wrong person performing unintended actions (actor-action mismatch), disordered social dynamics, and wrong action targets. To address these challenges, we present SocialDirector, a training-free interaction controller that enhances the generation model by modulating cross-attention maps. SocialDirector contains two modules: Social Actor Masking and Directional Reweighting. Social Actor Masking constrains each person's visual tokens to attend only to their own textual descriptions via a spatiotemporal mask, avoiding actor-action mismatch and disordered social dynamics. Directional Reweighting amplifies attention to directional words (e.g., "leftward", "right"), leading each action towards its intended target. To evaluate generated social interactions, we annotate existing datasets with interaction descriptions and build a fully automated evaluation pipeline powered by open-source VLMs. Experiments on different video generation models show that SocialDirector significantly improves interaction fidelity and approaches the upper bound set by real videos.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.10079
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.10079 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.10079 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.