DRAWER: Digital Reconstruction and Articulation With Environment Realism
This addresses the need for efficient digital replication in domains like gaming and robotics, offering a novel integrated solution for reconstruction and articulation.
The paper tackles the problem of converting videos of static indoor scenes into photorealistic and interactive digital environments, resulting in a framework that produces real-time, simulatable virtual replicas compatible with game engines and robotics platforms.
Creating virtual digital replicas from real-world data unlocks significant potential across domains like gaming and robotics. In this paper, we present DRAWER, a novel framework that converts a video of a static indoor scene into a photorealistic and interactive digital environment. Our approach centers on two main contributions: (i) a reconstruction module based on a dual scene representation that reconstructs the scene with fine-grained geometric details, and (ii) an articulation module that identifies articulation types and hinge positions, reconstructs simulatable shapes and appearances and integrates them into the scene. The resulting virtual environment is photorealistic, interactive, and runs in real time, with compatibility for game engines and robotic simulation platforms. We demonstrate the potential of DRAWER by using it to automatically create an interactive game in Unreal Engine and to enable real-to-sim-to-real transfer for robotics applications.