Affordance segmentation of hand-occluded containers from exocentric images

TL;DR

This paper introduces a novel affordance segmentation model that effectively handles hand-occlusions in third-person images by separately processing hand and object regions, improving segmentation accuracy and generalization.

Contribution

The paper proposes a new affordance segmentation approach with auxiliary branches for hand and object regions, trained on a newly annotated dataset with mixed-reality images.

Findings

Improved affordance segmentation accuracy over existing models

Better generalization to real and mixed-reality images

Effective handling of hand-occlusions in third-person views

Abstract

Visual affordance segmentation identifies the surfaces of an object an agent can interact with. Common challenges for the identification of affordances are the variety of the geometry and physical properties of these surfaces as well as occlusions. In this paper, we focus on occlusions of an object that is hand-held by a person manipulating it. To address this challenge, we propose an affordance segmentation model that uses auxiliary branches to process the object and hand regions separately. The proposed model learns affordance features under hand-occlusion by weighting the feature map through hand and object segmentation. To train the model, we annotated the visual affordances of an existing dataset with mixed-reality images of hand-held containers in third-person (exocentric) images. Experiments on both real and mixed-reality images show that our model achieves better affordance segmentation and generalisation than existing models.