Context-Constrained Accurate Contour Extraction for Occlusion Edge Detection
This work addresses occlusion edge detection for computer vision applications, representing an incremental improvement over existing CNN-based methods.
The paper tackles occlusion edge detection by proposing CCENet, which integrates spatial details and context constraints to filter noise and enhance contours, achieving state-of-the-art results on PIOD and BSDS datasets.
Occlusion edge detection requires both accurate locations and context constraints of the contour. Existing CNN-based pipeline does not utilize adaptive methods to filter the noise introduced by low-level features. To address this dilemma, we propose a novel Context-constrained accurate Contour Extraction Network (CCENet). Spatial details are retained and contour-sensitive context is augmented through two extraction blocks, respectively. Then, an elaborately designed fusion module is available to integrate features, which plays a complementary role to restore details and remove clutter. Weight response of attention mechanism is eventually utilized to enhance occluded contours and suppress noise. The proposed CCENet significantly surpasses state-of-the-art methods on PIOD and BSDS ownership dataset of object edge detection and occlusion orientation detection.