Techniques included in OpenCV​​​
  • Very fast Weighted Median Filter (WMF)

Weighted median, in the form of either solver or filter, has been employed in a wide range of computer vision solutions for its beneficial properties in sparsity representation. But it is hard to be accelerated due to the spatially varying weight and the median property. Our Weighted Median Filter (WMF) reduces computation complexity from O(r2) to O(r) where r is the kernel size. The contribution is on a new joint-histogram representation, median tracking, and a new data structure that enables fast data access. The effectiveness of these schemes is demonstrated on optical flow estimation, stereo matching, structure-texture separation, image filtering, to name a few. The running time is largely shortened from several minutes to less than 1 second. 

  • Scale-aware Rolling Guidance Filter (RGF)


Images contain many levels of important structures and edges. Compared to masses of research to make filters edge preserving, finding scale-aware local operations was seldom addressed in a practical way, albeit similarly vital in image processing and computer vision. Rolling Guidance Filter (RGF) filters images with the complete control of detail smoothing under a scale measure. It is based on a rolling guidance implemented in an iterative manner that converges quickly. RGF is simple in implementation, easy to understand, fully extensible to accommodate various data operations, and fast to produce results. The implementation of RGF achieves real-time performance and produces artifact-free results in separating different scale structures. This filter also introduces several inspiring properties different from previous edge-preserving ones.

  • L0 Image Smoothing


L0 Image Smoothing is particularly effective for sharpening major edges by increasing the steepness of transition while eliminating a manageable degree of low-amplitude structures. The seemingly contradictive effect is achieved in an optimization framework making use of L0 gradient minimization, which can globally control how many non-zero gradients are resulted in to approximate prominent structure in a sparsity-control manner. Unlike other edge-preserving smoothing approaches, L0 smoothing does not depend on local features, but instead globally locates important edges. It, as a fundamental tool, finds many applications and is particularly beneficial to edge extraction, clip-art JPEG artifact removal, and non-photorealistic effect generation.

  • Contrast Preserving Decolorization


Decolorization – the process to transform a color image to a grayscale one – is a basic tool in digital printing, stylized black-and-white photography, and in many single channel image processing applications. Our contrast preserving decolorization aims at maximally preserving the original color contrast. The main contribution is to alleviate a strict order constraint for color mapping based on human vision system, which enables the employment of a bimodal distribution to constrain spatial pixel difference and allows for automatic selection of suitable gray scale in order to preserve the original contrast. 

Deep Vision Lab

Deep Vision Lab

A top-tier research institute on computer vision and machine learning