Edit Propagation via Edge-Aware Filtering

This paper presents a novel framework for efficiently propagating the stroke-based user edits to the regions with similar colors and locations in high resolution images and videos. Our framework is based on the key observation that the edit propagation intrinsically can also be achieved by utilizing recently proposed edge-preserving filters. Therefore, instead of adopting the traditional global optimization which may involve a time-consuming solution, our algorithm propagates edits with the aid of the edge-preserve filters. Such a propagation scheme has low computational complexity and supports multiple kinds of strokes for more flexible user interactions. Further, our method can be easily and efficiently implemented in GPU. The experimental results demonstrate the efficiency and user-friendliness of our approach.

Edge-Aware Level Set Diffusion and Bilateral Filtering Reconstruction for Image Magnification

In this paper we propose an image magnification reconstruction method. In recent years many interpolation algorithms have been proposed for image magnification, but all of them have defects to some degree, such as jaggies and blurring. To solve these problems, we propose applying post-processing which consists of edge-aware level set diffusion and bilateral filtering. After the initial interpolation, the contours of the image are identified. Next, edge-aware level set diffusion is applied to these significant contours to remove the jaggies, followed by bilateral filtering at the same locations to reduce the blurring created by the initial interpolation and level set diffusion. These processes produce sharp contours without jaggies and preserve the details of the image. Results show that the overall RMS error of our method barely increases while the contour smoothness and sharpness are substantially improved.

Photographic Appearance Enhancement via Detail-Based Dictionary Learning

A number of edge-aware filters can efficiently boost the appearance of an image by detail decomposition and enhancement. However, they often fail to produce photographic enhanced appearance due to some visible artifacts, especially noise, halos and unnatural contrast. The essential reason is that the guidance and the constraint of high-quality appearance are not sufficient enough in the process of enhancement. Thus our idea is to train a detail dictionary from a lot of high-quality patches in order to constrain and control the entire appearance enhancement. In this paper, we propose a novel learning-based enhancement method for photographic appearance, which includes two main stages： dictionary training and sparse reconstruction. In the training stage, we construct a training set of detail patches extracted from some high-quality photos, and then train an overcomplete detail dictionary by iteratively minimizing an？1-norm energy function. In the reconstruction stage, we employ the trained dictionary to reconstruct the boosted detail layer, and further formalize a gradient-guided optimization function to improve the local coherence between patches. Moreover, we propose two evaluation metrics to measure the performance of appearance enhancement. The final experimental results have demonstrated the effectiveness of our learning-based enhancement method.

Fast and Error-Bounded Space-Variant Bilateral Filtering

The traditional space-invariant isotropic kernel utilized by a bilateral filter(BF)frequently leads to blurry edges and gradient reversal artifacts due to tlie existence of a large amount of outliers in the local averaging window.However,the efficient and accurate cstiinatioii of space-variant k(4rnels which adapt to image structures,and the fast realization of the corresponding space-variant bilateral filtering are challenging problems.To address these problems,we present a space-variant BF(SVBF).and its linear time and error-bounded acceleration method.First,we accurately estimate spacevariant,anisotropic kernels that vary with image structures in linear time through structure tensor and mininnini spanning tree.Second,we perform SVBF in linear time using two error-bounded approximation methods,namely,low-rank tensor approximation via higher-order singular value decomposition and exponential sum approximation.Tlierefore.the proposed SVBF can efficiently achieve good edge-preserving results.We validate the advantages of the proposed filter in applications including:image denoising,image enhancement,and image focus editing.Experimental results(leinonstrate that our fast and error-bounded SVBF is superior to state-of-the-art methods.