Real-time edge-aware image processing with the bilateral grid

By Jiawen Chen, Sylvain Paris, Frédo Durand. ACM Transactions on Graphics, 2007

631 citations recorded by the source corpus.

We present a new data structure---the bilateral grid, that enables fast edge-aware image processing. By working in the bilateral grid, algorithms such as bilateral filtering, edge-aware painting, and local histogram equalization become simple manipulations that are both local and independent. We parallelize our algorithms on modern GPUs to achieve real-time frame rates on high-definition video. We demonstrate our method on a variety of applications such as image editing, transfer of photographic look, and contrast enhancement of medical images.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4ef0a1200a1d9e69a291184d5c4c7cffc562135f

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Medical image processing on the GPU - Past, present and future (2013, methodology): “Chen et al. (2007) used a GPU to perform bilateral filtering on images of the resolution 1920 × 1080 at 30 Hz.”
Manipulating Attributes of Natural Scenes via Hallucination (2018, methodology): “2, for DPST-based stylized images, we first apply a cross bilateral filter (BLF) [Chen et al. 2007] and then employ screened Poisson equation (SPE)-based photorealism enhancement approach [Mechrez et al.”
Image smoothing via L0 gradient minimization (2011, methodology): “Edge-preserving smoothing can be achieved by local filtering, including bilateral filtering [Tomasi and Manduchi 1998], its accelerated versions [Paris and Durand 2006; Weiss 2006; Chen et al. 2007] and relatives [Choudhury and Tumblin 2003; Fattal 2009; Baek and Jacobs 2010; Kass and Solomon 2010].”
Depth-aware CNN for RGB-D Segmentation (2018, methodology): “Bilateral filters [3,2] is widely used in computer graphics for image smoothness with edge preserving.”
Color Constancy, Intrinsic Images, and Shape Estimation (2012, methodology): “Note that this formulation is extremely similar to the bilateral grid [3], which is a tool for high-dimensional Gaussian ﬁltering (used mostly for bilateral ﬁlter-ing, hence the name).”
A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach (2006, methodology): “We also refer readers to our recent work that extends the image representation described in this article to other edge-aware applications beyond bilateral filtering such as scribble interpolation, painting, and local histogram equalization (Chen et al. 2007).”
Fast Image Processing with Fully-Convolutional Networks (2017, background): “The bilateral filter in particular has benefitted from long-term investment in its acceleration [21, 72, 15, 59, 2, 1, 29, 8].”
Sparse Dictionary Learning for Edit Propagation of High-Resolution Images (2014, background): “Also related are a large body of works on edge-aware or edge-centric image processing [5, 11] and image upsampling techniques [12].”
Paint selection (2009, methodology): “In approaches like Intelligent Paint [Reese 1999], Bilateral Grid [Chen et al. 2007], and Edgerespecting Brushes [Olsen and Harris 2008], users directly paint the object using a brush.”
Real-time O(1) bilateral filtering (2009, methodology): “interactive speed or even video rate using GPU (Graphics Processing Unit) implementation [21].”
Rolling Guidance Filter (2014, neutral): “Average-based filters include anisotropic diffusion [20], bilateral filter [26,8,19,6,32,33], guided filter [13], and geodesic filters [7,11].”