Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling

TL;DR

Picasso is a physics-constrained scene reconstruction method that holistically reasons over object interactions to produce physically plausible and accurate 3D scene models, aiding simulation and planning.

Contribution

The paper introduces Picasso, a novel reconstruction pipeline that incorporates physics constraints and a contact graph to improve scene plausibility and accuracy.

Findings

Picasso outperforms existing methods in physical plausibility and accuracy.

The Picasso dataset provides real-world scenes with ground truth for benchmarking.

Reconstructed scenes are more aligned with human intuition and physically consistent.

Abstract

In the presence of occlusions and measurement noise, geometrically accurate scene reconstructions -- which fit the sensor data -- can still be physically incorrect. For instance, when estimating the poses and shapes of objects in the scene and importing the resulting estimates into a simulator, small errors might translate to implausible configurations including object interpenetration or unstable equilibrium. This makes it difficult to predict the dynamic behavior of the scene using a digital twin, an important step in simulation-based planning and control of contact-rich behaviors. In this paper, we posit that object pose and shape estimation requires reasoning holistically over the scene (instead of reasoning about each object in isolation), accounting for object interactions and physical plausibility. Towards this goal, our first contribution is Picasso, a physics-constrained reconstruction pipeline that builds multi-object scene reconstructions by considering geometry, non-penetration, and physics. Picasso relies on a fast rejection sampling method that reasons over multi-object interactions, leveraging an inferred object contact graph to guide samples. Second, we propose the Picasso dataset, a collection of 10 contact-rich real-world scenes with ground truth annotations, as well as a metric to quantify physical plausibility, which we open-source as part of our benchmark. Finally, we provide an extensive evaluation of Picasso on our newly introduced dataset and on the YCB-V dataset, and show it largely outperforms the state of the art while providing reconstructions that are both physically plausible and more aligned with human intuition.