Verified65% confidenceFactExact time
2024年Google DeepMind的Genie系列可仅凭单张图像生成可交互的2D/3D游戏环境
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
7/10/2026
First Seen
Valid until: 10/8/2026
Sources
MIRA：基于火箭联盟的多人交互世界模型解析
hackernewshackernews7/9/2026
Related Claims
UnverifiedGoogle DeepMind的Genie 1基于从互联网视频中无监督学习的潜在动作空间(Latent Action Model)，无需动作标注即可从视频帧序列自动发现虚拟控制器70% similarUnverified阿里巴巴旗下高德发布通用世界模型World Studio并开放测试，将交互式视频生成与3DGS场景生成统一在同一平台，输出可保存为视频与3DGS文件64% similarUnverifiedGenie 2扩展至3D场景，仅凭单张图像即可生成具备一致性物理规律、支持多种视角交互的3D世界，且生成速度达到实时64% similarUnverified推荐独立开发者原型阶段用免费快速工具如Hunyuan 3D，精修阶段再换用拓扑质量更高的Hi3D或视觉表现更强的Yovo 3D64% similarUnverifiedDeepSeek V4 Pro在3D跑酷游戏任务中加入了镜头跟随和音效功能，表现超出预期64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/418945API
curl https://kongchang.com/api/v1/knowledge/claims/418945MCP
get_claim(id=418945)