cs.CVNov 11, 2026

CoCode-World: Shared 3D Proxy Representation for Multi-Player World Models

Authors: Qirui Li, Xin Zhang, Yabo Chen, Jinkun Hao, Paul L Rosin, Yu-Kun Lai, Haibin Huang, Yin Chen, 

Organizations: Shanghai Jiao Tong University · Institute of Artificial Intelligence, China Telecom (TeleAI) · Cardiff University

Abstract

Multiplayer generative world models must produce observations that agree on shared entities despite different camera motions and occlusions. Explicit world representations provide spatial control, but precise modeling of individual game maps limits scene diversity, while shared geometry alone cannot ensure consistent appearance across views. We present CoCode-World, a shared 3D proxy framework that separates structural control from visual synthesis for two-player video generation. Programmable proxies specify scene layout, motion, and occlusion, while RGB references guide character and scene appearance. To coordinate visual details across players, we concatenate paired proxy videos, appearance references, and target views in a consistent spatial layout and generate both views jointly with a pretrained video model. This formulation uses the model's native attention for cross-view communication within a single generation branch, with LoRA adaptation learning proxy adherence and appearance correspondence from paired observations. We construct a two-player GTA~V dataset that pairs synchronized RGB observations with proxy videos derived from shared map geometry and game-engine state. Experiments demonstrate appearance transfer to characters and scene styles unseen during training, with improvements in video quality and cross-view player identity over the evaluated baseline. Ablations further examine how proxy construction and cross-view communication affect generation. Project page: https://iapple233.github.io/CCW/.

Figures & tables

Explore similar work

CardsList
  1. WorldCast: Distributed Multiplayer World Models

    Oct 8, 2026Ziyang Ye, Junchao Huang, Evelyn Zhang +9World ModelsInteractive World Models

  2. ShareVerse: Multi-Agent Consistent Video Generation for Shared World Modeling

    Mar 3, 2026Jiayi Zhu, Jianing Zhang, Yiying Yang +2Video World ModelsMulti-View Video Generation