DDNet: Dual-path Decoder Network for Occlusion Relationship Reasoning
arXiv:1911.11582
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.
arXiv commentThe new one has been republished as arXiv:2108.05722
References in corpus (7)
- Deep Residual Learning for Image Recognition
- Richer Convolutional Features for Edge Detection
- Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
- Monocular Object Instance Segmentation and Depth Ordering with CNNs
- Learning to predict crisp boundaries
- Context-Constrained Accurate Contour Extraction for Occlusion Edge Detection
- DOC: Deep OCclusion Estimation From a Single Image