Continuous 3D Perception Model with Persistent State
This work addresses the challenge of real-time, unified 3D scene understanding for applications like robotics and augmented reality, though it appears incremental as it builds on existing recurrent and transformer-based methods.
The paper tackles the problem of continuous 3D perception from image streams by introducing a stateful recurrent model that updates its state with each observation, enabling online generation of metric-scale pointmaps and coherent scene reconstructions, achieving competitive or state-of-the-art performance across various 3D/4D tasks.
We present a unified framework capable of solving a broad range of 3D tasks. Our approach features a stateful recurrent model that continuously updates its state representation with each new observation. Given a stream of images, this evolving state can be used to generate metric-scale pointmaps (per-pixel 3D points) for each new input in an online fashion. These pointmaps reside within a common coordinate system, and can be accumulated into a coherent, dense scene reconstruction that updates as new images arrive. Our model, called CUT3R (Continuous Updating Transformer for 3D Reconstruction), captures rich priors of real-world scenes: not only can it predict accurate pointmaps from image observations, but it can also infer unseen regions of the scene by probing at virtual, unobserved views. Our method is simple yet highly flexible, naturally accepting varying lengths of images that may be either video streams or unordered photo collections, containing both static and dynamic content. We evaluate our method on various 3D/4D tasks and demonstrate competitive or state-of-the-art performance in each. Project Page: https://cut3r.github.io/