Deepmind 把视频生成器当成通用感知模型，用合成视频训练就达到了顶级深度估计水平，挺震撼的，值得一看。
Google Deepmind 提出 GenCeption 方法，利用视频生成器完成深度估计和语义分割等经典视觉任务。该方法在仅使用合成视频训练的情况下，匹配甚至超越当前最先进系统的性能。研究团队认为视频生成器内部已经隐式包含了一种通用世界模型，这挑战了传统计算机视觉的范式。GenCeption 在 KITTI 深度估计基准上取得了与基于真实数据训练的模型相当的结果，证明了其有效性。
Google Deepmind argues video generators already contain the world models computer vision has been missing
Google Deepmind's GenCeption repurposes a video generator for classic vision tasks such as depth estimation and segmentation, matching state-of-the-art systems with far less training data. The model trained almost entirely on synthetic videos. Its results add to the debate over whether video generators already contain a kind of universal world model. The article Google Deepmind argues video generators already contain the world models computer vision has been missing appeared first on The Decoder .