GameGen-X: Interactive Open-world Game Video Generation
Haoxuan Che, Xuanhua He, Quande Liu, Cheng Jin, Hao Chen
摘要
We introduce GameGen-X, the first diffusion transformer model specifically designed for both generating and interactively controlling open-world game videos. This model facilitates high-quality, open-domain generation by simulating an extensive array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, predicting and altering future content based on the current clip, thus allowing for gameplay simulation. To realize this vision, we first collected and built an Open-World Video Game Dataset (OGameData) from scratch. It is the first and largest dataset for open-world game video generation and control, which comprises over one million diverse gameplay video clips with informative captions from GPT-4o. GameGen-X undergoes a two-stage training process, consisting of pre-training and instruction tuning. Firstly, the model was pre-trained via text-to-video generation and video continuation, endowing it with the capability for long-sequence, high-quality open-domain game video generation. Further, to achieve interactive controllability, we designed InstructNet to incorporate gamerelated multi-modal control signal experts. This allows the model to adjust latent representations based on user inputs, unifying character interaction, and scene content control for the first time in video generation. During instruction tuning, only the InstructNet is updated while the pre-trained foundation model is frozen, enabling the integration of interactive controllability without loss of diversity and quality of generated content. GameGen-X represents a significant leap forward in open-world game design using generative models. It demonstrates the potential of generative models to serve as auxiliary tools to traditional rendering techniques, effectively merging creative generation with interactive capabilities. The project will be available at https://github.com/GameGen-X/GameGen-X .
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper37
- Video World Models with Long-term Spatial MemoryTong Wu, Shuai Yang, Ryan Po, Yinghao Xu 等NeurIPS 2025 · 被引用 145 次
- Unified Vision-Language-Action ModelYuqi Wang, Xinghang Li, Wenxuan Wang, Junbo Zhang 等ICLR 2026 · 被引用 144 次
- WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World ModelingWenqiang Sun, Haiyu Zhang, Haoyuan Wang, Junta Wu 等ICML 2026 · 被引用 108 次
- The Matrix: Infinite-Horizon World Generation with Real-Time Moving ControlRuili Feng, Han Zhang, Zhilei Shu, Zhantao Yang 等NeurIPS 2025 · 被引用 92 次
- Stable Video Infinity: Infinite-Length Video Generation with Error RecyclingWuyang Li, Wentao Pan, Po-Chien Luan, Yang Gao 等ICLR 2026 · 被引用 69 次
它引用的顶会 Paper27
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 被引用 11,743 次
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 被引用 5,568 次
相关 Paper
- GameFactorly: Creating New Games with Generative Interactive VideosJiwen Yu, Yiran Qin, Xintao Wang, Pengfei Wan 等ICCV 2025 · 被引用 7 次
- Pre-Trained Video Generative Models as World SimulatorsHaoran He, Yang Zhang, Liang Lin, Zhongwen Xu 等AAAI 2026 · 被引用 32 次
- GenHowTo: Learning to Generate Actions and State Transformations from Instructional VideosTomás Soucek, Dima Damen, Michael Wray, Ivan Laptev 等CVPR 2024 · 被引用 9 次
- Genie: Generative Interactive EnvironmentsJake Bruce, Michael D. Dennis, Ashley Edwards, Jack Parker-Holder 等ICML 2024 · 被引用 513 次
- Modular-Cam: Modular Dynamic Camera-view Video Generation with LLMZirui Pan, Xin Wang, Yipeng Zhang, Hong Chen 等AAAI 2025 · 被引用 6 次
