DeepMind 发布 D4RT：统一 4D 场景重建与跟踪模型

AI 摘要

Google DeepMind 推出了 D4RT，一个用于 4D 场景重建与跟踪的统一 AI 模型，能够从 2D 视频中恢复动态三维世界。该模型采用编码器-解码器 Transformer 架构和查询机制，比以往方法高效 300 倍，适用于机器人、增强现实等实时应用。

正文节选

Introducing D4RT, a unified AI model for 4D scene reconstruction and tracking across space and time. Anytime we look at the world, we perform an extraordinary feat of memory and prediction. We see and understand things as they are at a given moment in time, as they were a moment ago, and how they are going to be in the moment to follow. Our mental model of the world maintains a persistent representation of reality and we use that model to draw intuitive conclusions about the causal relationship

发布时间：2026-01-16 18:39

抓取时间：2026-09-07 03:44

来源机构：Google DeepMind