A Computational Model for Amodal Completion

TL;DR

This paper introduces a computational model that reconstructs 3D scene structure from 2D images, effectively inferring occluded objects and their depth order by integrating perceptually inspired cues and Bayesian inference.

Contribution

It presents a novel method combining elastica-based disocclusion and Bayesian modeling to interpret occluded scenes from planar images, advancing scene reconstruction techniques.

Findings

Successfully reconstructs occluded objects in synthetic and real images.

Accurately infers depth ordering of objects in complex scenes.

Performs well on Berkeley dataset with ground-truth labels.

Abstract

This paper presents a computational model to recover the most likely interpretation of the 3D scene structure from a planar image, where some objects may occlude others. The estimated scene interpretation is obtained by integrating some global and local cues and provides both the complete disoccluded objects that form the scene and their ordering according to depth. Our method first computes several distal scenes which are compatible with the proximal planar image. To compute these different hypothesized scenes, we propose a perceptually inspired object disocclusion method, which works by minimizing the Euler's elastica as well as by incorporating the relatability of partially occluded contours and the convexity of the disoccluded objects. Then, to estimate the preferred scene we rely on a Bayesian model and define probabilities taking into account the global complexity of the objects in the hypothesized scenes as well as the effort of bringing these objects in their relative position in the planar image, which is also measured by an Euler's elastica-based quantity. The model is illustrated with numerical experiments on, both, synthetic and real images showing the ability of our model to reconstruct the occluded objects and the preferred perceptual order among them. We also present results on images of the Berkeley dataset with provided figure-ground ground-truth labeling.