no code implementations • ICCV 2015 • Longquan Dai, Mengke Yuan, Feihu Zhang, Xiaopeng Zhang
This paper presents a linear time fully connected guided filter by introducing the minimum spanning tree (MST) to the guided filter (GF).
no code implementations • ICCV 2015 • Feihu Zhang, Longquan Dai, Shiming Xiang, Xiaopeng Zhang
In our SGF, we use the tree distance on the segment graph to define the internal weight function of the filtering kernel, which enables the filter to smooth out high-contrast details and textures while preserving major image structures very well.
no code implementations • 30 May 2017 • Longquan Dai
In this paper, we will disclose that the Guided Filter (GF) can be interpreted as the Cyclic Coordinate Descent (CCD) solver of a Least Square (LS) objective function.
no code implementations • CVPR 2017 • Longquan Dai, Mengke Yuan, Zechao Li, Xiaopeng Zhang, Jinhui Tang
In this paper we propose a hardware-efficient Guided Filter (HGF), which solves the efficiency problem of multichannel guided image filtering and yields competent results when applying it to multi-label problems with synthesized polynomial multichannel guidance.
no code implementations • 28 Feb 2018 • Longquan Dai, Mengke Yuan, Xiaopeng Zhang
To achieve the constant-time BF whose complexity is irrelevant to the kernel size, many techniques have been proposed, such as 2D box filtering, dimension promotion, and shiftability property.
no code implementations • NeurIPS 2018 • Longquan Dai, Liang Tang, Yuan Xie, Jinhui Tang
Over the decades, people took a handmade approach to design fast algorithms for the Gaussian convolution.