DailyArt: Discovering Articulation from Single Static Images via Latent Dynamics
This work addresses a challenging problem in embodied AI and world models for robotics and simulation, offering a novel method that reduces reliance on multi-state observations or explicit priors, though it is incremental in advancing single-image articulation inference.
The paper tackles the problem of inferring articulated joint parameters from a single static image of an object in a closed state, where motion cues are occluded, by first synthesizing an opened state to expose articulation cues and then estimating joints from the discrepancy, achieving strong performance in joint estimation and supporting part-level novel state synthesis.
Articulated objects are essential for embodied AI and world models, yet inferring their kinematics from a single closed-state image remains challenging because crucial motion cues are often occluded. Existing methods either require multi-state observations or rely on explicit part priors, retrieval, or other auxiliary inputs that partially expose the structure to be inferred. In this work, we present DailyArt, which formulates articulated joint estimation from a single static image as a synthesis-mediated reasoning problem. Instead of directly regressing joints from a heavily occluded observation, DailyArt first synthesizes a maximally articulated opened state under the same camera view to expose articulation cues, and then estimates the full set of joint parameters from the discrepancy between the observed and synthesized states. Using a set-prediction formulation, DailyArt recovers all joints simultaneously without requiring object-specific templates, multi-view inputs, or explicit part annotations at test time. Taking estimated joints as conditions, the framework further supports part-level novel state synthesis as a downstream capability. Extensive experiments show that DailyArt achieves strong performance in articulated joint estimation and supports part-level novel state synthesis conditioned on joints. Project page is available at https://rangooo123.github.io/DaliyArt.github.io/.