Models · Research · Applications
World Labs发布Atlas：单一AI模型仅凭几张照片即可生成、重建并模拟3D世界
World Labs发布Atlas，一个世界模型，能够从少量图像生成、重建和模拟3D场景，无需特殊采集设备，并在人工评估中优于多个竞品。
阅读 THE DECODER 原文为什么重要
Atlas展示了AI在3D内容生成和世界建模方面的突破，可能推动游戏、影视、机器人等领域的创新。
关键事实
事实 1
Atlas由AI研究员李飞飞联合创办的World Labs公司发布。
来源与依据
World Labs, co-founded by AI researcher Fei-Fei Li, has announced Atlas, a world model that generates, reconstructs, and simulates 3D scenes from just a few images.
事实 2
Atlas可从最少一张到几十张输入图像重建真实场景，无需特殊采集设备。
来源与依据
Atlas rebuilds real scenes from as few as one to several dozen input images without special capture equipment.
事实 3
在相机控制生成的人工评估中，Atlas在与MiniMax H3的对比中有75%的比较获得人类评估者偏好。
来源与依据
Human evaluators preferred Atlas in 75 percent of comparisons against MiniMax H3, 81 percent against Gemini Omni Flash, 86 percent against Happy Horse 1.1, 93 percent against, and 94 percent against Seedance 2.5.