In this paper, we propose a learning-based approach to the task of automatically extracting
a" wireframe" representation for images of cluttered man-made environments. The wireframe …

Compared to feature point detection and description, detecting and matching line segments
offer additional challenges. Yet, line features represent a promising complement to points for …

Optical character recognition (OCR) is an important research area in the field of pattern
recognition. A lot of research has been done on OCR in the last 60 years. There is a large …

The human visual system reliably extracts shape information from complex natural scenes in
spite of noise and fragmentation caused by clutter and occlusions. A fast, feedforward sweep …

We introduce a new photographing guidance (PhotoHelper) for amateur photographers to
enhance their portrait photo quality using deep feature retrieval and fusion. In our model, we …

This paper presents a fast and parsimonious parsing method to accurately and robustly
detect a vectorized wireframe in an input image with a single forward pass. The proposed …

This paper presents a region-partition based attraction field dual representation for line
segment maps, and thus poses the problem of line segment detection (LSD) as the region …

Classical work on line segment detection is knowledge-based; it uses carefully designed
geometric priors using either image gradients, pixel groupings, or Hough transform variants …

In this paper, we present a novel framework to detect line segments in man-made
environments. Specifically, we propose to describe junctions, line segments and …

Previous deep learning-based line segment detection (LSD) suffers from the immense
model size and high computational cost for line prediction. This constrains them from real …