DDNet: Dual-path Decoder Network for Occlusion Relationship Reasoning

TL;DR

This paper introduces DDNet, a dual-path decoder network that effectively separates occlusion boundary extraction and orientation inference, utilizing a novel orthogonal orientation representation and multi-scale loss to achieve state-of-the-art results.

Contribution

The paper proposes a dual-path decoder architecture with orthogonal orientation representation and specialized loss functions for improved occlusion reasoning.

Findings

Achieves state-of-the-art results on PIOD and BSDS datasets.

Effectively separates boundary and orientation tasks in occlusion reasoning.

Introduces orthogonal orientation regression loss for better orientation learning.

Abstract

Occlusion relationship reasoning based on convolution neural networks consists of two subtasks: occlusion boundary extraction and occlusion orientation inference. Due to the essential differences between the two subtasks in the feature expression at the higher and lower stages, it is challenging to carry on them simultaneously in one network. To address this issue, we propose a novel Dual-path Decoder Network, which uniformly extracts occlusion information at higher stages and separates into two paths to recover boundary and occlusion orientation respectively in lower stages. Besides, considering the restriction of occlusion orientation presentation to occlusion orientation learning, we design a new orthogonal representation for occlusion orientation and proposed the Orthogonal Orientation Regression loss which can get rid of the unfitness between occlusion representation and learning and further prompt the occlusion orientation learning. Finally, we apply a multi-scale loss together with our proposed orientation regression loss to guide the boundary and orientation path learning respectively. Experiments demonstrate that our proposed method achieves state-of-the-art results on PIOD and BSDS ownership datasets.