Unverified85% confidenceFactExact time
Project Genie此前已展示了从单张图片生成可玩游戏关卡的能力
1
Sources
85%
Confidence
Long-term
Relevance
5/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedProject Genie的核心能力是通过AI从图像、文本等输入中生成可交互的虚拟环境，不需要开发者手动搭建场景74% similarUnverifiedGenie的核心技术创新是潜在动作模型（LAM），使用VQ-VAE将帧间差异量化为离散动作符号，无需人工标注动作标签即可生成可交互2D游戏环境71% similarUnverifiedGenie 2 extends to 3D scenes, generating 3D worlds with consistent physical laws that support multi-perspective interaction from a single image alone, at real-time generation speed.70% similarVerifiedIn 2024, Google DeepMind's Genie series can generate interactive 2D/3D game environments from a single image alone.62% similarUnverifiedDoubao's "Plaza" showcases works by other users, including 3D games.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/10669API
curl https://kongchang.com/api/v1/knowledge/claims/10669MCP
get_claim(id=10669)