Single-image system creates interactive 3D tabletop scenes with moving parts
ArticuTable: Generating Instance-Level Interactive Rigid-Articulated 3D Tabletop Scenes from a Single Image
Computer Vision and Pattern Recognition
Summary
Many 3D models from single images treat objects as simple solid pieces, which makes it hard to simulate realistic movements like opening a drawer. The authors present ArticuTable, which can turn one photo of a tabletop scene into a detailed 3D scene where parts of objects can move naturally. They address challenges in guessing exact positions and sizes from one view and teach the system to understand how parts connect and move. They also provide 100 example scenes ready to use in simulations. Their tests show the system produces visually accurate, physically plausible scenes that behave well in interactive settings.
What this means in practice
- •For robotics developers: Generate detailed 3D tabletop scenes with movable parts from a single image for robot interaction and manipulation testing.
- •For game designers: Create interactive 3D tabletop environments that maintain realistic object articulation and positioning from simple image inputs.
Authors
Kai Lv, Yibo Yin, Lijun Guo, Heng Fan, Kaihao Zhang, Xingping Dong
Abstract
Embodied agents benefit from 3D environments that combine visual fidelity to real-world observations with physical interactivity. Existing single-image tabletop reconstruction methods recover plausible scene geometry but typically represent objects as monolithic rigid bodies, limiting interaction to whole-object rigid motion and precluding executable part-level articulation. Meanwhile, recovering a scene layout consistent with the input view remains challenging because a single observation may admit multiple plausible pose-scale configurations. We present ArticuTable, a single-image 3D tabletop reconstruction framework that recovers both executable part-level articulation and an input-view-consistent scene layout. For object modeling, we introduce generation-robust articulation modeling (GRAM), which combines joint fitting guided by a multimodal large language model with semantic state reasoning to recover reliable joint parameters and valid motion ranges from imperfect monolithic proxy meshes, thereby converting them into executable articulated assets. For scene layout, we introduce progressive semantic-geometric scene registration (PSGSR), which progressively narrows the pose-scale search space under complementary metric, planar, and input-view constraints and resolves orientation ambiguity through structure-aware semantic correspondences, yielding a scene layout consistent with the input view. We further contribute ArticuTable-100, a curated collection of 100 simulation-ready tabletop scenes. Extensive evaluation, including a user study, demonstrates strong performance across visual fidelity, input-view consistency, articulation quality, physical plausibility, and simulation readiness.