From a Modified Ambrosio-Tortorelli to a Randomized Part Hierarchy Tree

TL;DR

This paper introduces a novel method for coding higher-level parts in images using a modified Ambrosio-Tortorelli model, organizing them into a probabilistic binary tree to improve visual processing tasks.

Contribution

It extends the AT model by incorporating a non-local interaction term and probabilistic structure, enabling hierarchical part coding beyond simple boundary detection.

Findings

Hierarchical part organization as a binary tree.

Handling of non-generic configurations and occlusions.

Probabilistic structure improves robustness.

Abstract

We demonstrate the possibility of coding parts, features that are higher level than boundaries, using a modified AT field after augmenting the interaction term of the AT energy with a non-local term and weakening the separation into boundary/not-boundary phases. The iteratively extracted parts using the level curves with double point singularities are organized as a proper binary tree. Inconsistencies due to non-generic configurations for level curves as well as due to visual changes such as occlusion are successfully handled once the tree is endowed with a probabilistic structure. The work is a step in establishing the AT function as a bridge between low and high level visual processing.