Domain transform for edge-aware image and video processing

By Eduardo Simoes Lopes Gastal, M. M. O. Neto. 2011

855 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Attention to Scale: Scale-Aware Semantic Image Segmentation (2015, methodology): “Recently, [10] has been shown that further improvement can be attained by combining our proposed model and a discriminatively trained domain transform [23].”
Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform (2015, methodology): “In this paper, we propose replacing the fully-connected CRF and its associated bilateral filtering with the domain transform (DT) [16], an alternative edge-aware filter.”
Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes (2016, neutral): “Other approaches to smoothing the network predictions include domain transform [8, 19] and superpixel-based smoothing [16, 39].”
Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network (2016, methodology): “As such, recursive implementations are commonly exploited to accelerate image filtering methods, such as spatially invariant/variant Gaussian filters [1,2,3], bilateral filters [4] and domain transforms [5].”
The Fast Bilateral Solver (2015, methodology): “though simpler and faster edge-aware upsampling or filtering techniques [9, 15, 18] perform reasonably for this task.”
Deep Colorization (2015, methodology): “As a result, it is smoothed using an efﬁcient edge-preserving ﬁlter [26] with the guidance of the original gray scale image.”
PCA-Based Edge-Preserving Features for Hyperspectral Image Classification (2017, methodology): “Experimental results presented in [46] show that artifact-free filtered images can be obtained by”
NIMA: Neural Image Assessment (2017, methodology): “Turbo denoising [44] is a technique which uses the domain transform [45] as its core filter.”
Intel RealSense Stereoscopic Depth Cameras (2017, background): “Additionally, the use of the color data to smooth and in-paint the depth data with an edge-preserving blur is often helpful, such as with a domain transform [3].”
Guided Image Filtering (2010, background): “But the kernels of the wavelets are sparsely distributed in the image plane, with constrained kernel sizes (to powers of two), which may limit the applications.”
Pixel-Adaptive Convolutional Neural Networks (2019, background): “[30] propose differentiable local propagation modules that have roots in domain transform ﬁl-tering [14].”
Survey on semantic segmentation using deep learning techniques (2019, background): “The second module named Edge Net, predicts edge features from midway layers and the third module is an edge-preserving ﬁlter named Domain Transform (recursive ﬁltering), proposed in [179].”
Spectral–Spatial Hyperspectral Image Classification With Edge-Preserving Filtering (2014, methodology): “In this section, the two most widely used EPFs, i.e., the joint bilateral filter and the guided filter, are illustrated.”
A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing (2017, methodology): “To answer this question, we replaced I-CNN with the Domain Trans-form (DT) technique [10].”
Gated-SCNN: Gated Shape CNNs for Semantic Segmentation (2019, methodology): “To avoid costly DenseCRF [29], the work of [6] uses fast domain transform [16] ﬁltering on network output while also predicting edge maps from intermediate CNN layers.”
Robust Multi-Exposure Image Fusion: A Structural Patch Decomposition Approach (2017, background): “H. Li and L. Zhang are with the Department of Computing, The Hong Kong Polytechnic University, Hong Kong (e-mail: cshli@comp.polyu.edu.hk; cslzhang@comp.polyu.edu.hk).”