Shuai Fang

Improved single image dehazing using segmentation

In the hazy weather, the image of outdoor scene is degraded by suspended particles. Scattering and absorption hinder scene radiance and bring in environment light into camera. In this work, a novel algorithm is introduced to restore the clear day image by the segmented hazy image. First, the existing visibility restoration model is analyzed and a conclusion is drawn that the model will violate the contrast enhancement constraint in some specific situations. Next, the graph-based image segmentation method is applied to segment the hazed image by choosing the optimal parameter. Then, the transmission maps prior are obtained according to the blackbody theory. After that, a bilateral filter is designed to amend the transmission map, which can make up the deficiency of restoration model and ensure the transmission map smooth under the contrast enhancement constraint. Last, the experimental results show that the method achieves rather good dehazing results.

Digital Multi-Focusing From a Single Photograph Taken With an Uncalibrated Conventional Camera

The demand to restore all-in-focus images from defocused images and produce photographs focused at different depths is emerging in more and more cases, such as low-end hand-held cameras and surveillance cameras. In this paper, we manage to solve this challenging multi-focusing problem with a single image taken with an uncalibrated conventional camera. Different from all existing multi-focusing approaches, our method does not need to include a deconvolution process, which is quite time-consuming and will cause ringing artifacts in the focused region and low depth-of-field. This paper proposes a novel systematic approach to realize multi-focusing from a single photograph. First of all, with the optical explanation for the local smooth assumption, we present a new point-to-point defocus model. Next, the blur map of the input image, which reflects the amount of defocus blur at each pixel in the image, is estimated by two steps. 1) With the sharp edge prior, a rough blur map is obtained by estimating the blur amount at the edge regions. 2) The guided image filter is applied to propagate the blur value from the edge regions to the whole image by which a refined blur map is obtained. Thus far, we can restore the all-in-focus photograph from a defocused input. To further produce photographs focused at different depths, the depth map from the blur map must be derived. To eliminate the ambiguity over the focal plane, user interaction is introduced and a binary graph cut algorithm is used. So we introduce user interaction and use a binary graph cut algorithm to eliminate the ambiguity over the focal plane. Coupled with the camera parameters, this approach produces images focused at different depths. The performance of this new multi-focusing algorithm is evaluated both objectively and subjectively by various test images. Both results demonstrate that this algorithm produces high quality depth maps and multi-focusing results, outperforming the previous approaches.

Image quality assessment on image haze removal

In the hazy weather, the image of outdoor scene is degraded by suspended particles. Recently, great progresses have been made on single image haze removal. Therefore an accurate quality metric is required. Although image quality assessment has been extensively studied these past few decades, few methods can be applied in this area since there is no reference image. This paper proposed an evaluation metric combining the ascension of contrast degree with the structural similarity to deal with the problem. The ascension of the contrast degree and the structural similarity are computed respectively based on the spatial frequency contrast and the edges consistency between the hazy and the dehazed image. At last, we evaluate the state-of-the-art image haze removal methods based on our evaluation metric.

Adaptive removal of real noise from a single image

Abstract. Although state-of-the-art image denoising algorithms have achieved outstanding results, removing real, color noise from a single image remains a challenging problem. An adaptive image denoising algorithm that integrates a constant time bilateral filter with noise-level estimation is proposed. The estimation of the noise-level function (NLF), which describes the noise level as a function of image brightness, is the key to ensure the removal of the color noise. To achieve this aim, a bilateral median filter is exploited to estimate the upper bound of NLF by fitting a lower envelope to the standard deviations of per-segment image variances. Furthermore, we make an empirical study on the relationship between the optimal parameter of constant time bilateral filter and the noise level. Then, an adaptive denoising algorithm, where the filtering parameter is automatically adjusted according to the estimated noise level, is conducted to obtain the underlying clean image from the noisy input. In addition, we present a new method of synthesizing noise, where the synthetic noise is very close to the real noise. Meanwhile, we test our algorithm on the synthetic noise images and on the real applications as well. Various experimental results show that our algorithm outperforms state-of-the-art denoising algorithms in eliminating real, color noise.

Single Image Multi-focusing Based on Local Blur Estimation

In this paper, we address a challenging problem of multi-focusing image from a single photograph taken with an uncalibrated conventional camera. In order to achieve this, we firstly derive an optical degradation model which enables us to adopt a point operation scheme to realize image multi-focusing. This scheme can effectively reduce halo artifacts in the refocused image and greatly improve the computational efficiency. Then, a two-step approach is applied to estimate the blur map of the input image. i). A sparse blur map is obtained by estimating the amount of defocus blur at edge locations. ii). The guided image filtering method is applied to propagate the value from edge locations into the unknown regions. In order to obtain the depth map of the whole scene to realize the multi-focusing, we adopt a simple geometry prior of photograph to eliminate the ambiguity over the focal plane. Based on the obtained depth map, we can directly produce different styles of images by multi-focusing with the adjustment to the camera parameters. Experimental results on a variety of images show that our method can acquire visual pleasing multi-focusing results. Moreover, our method can also extract the depth map of the scene with fairly good extent of accuracy.

Fast Haze Removal for Nighttime Image Using Maximum Reflectance Prior

In this paper, we address a haze removal problem from a single nighttime image, even in the presence of varicolored and non-uniform illumination. The core idea lies in a novel maximum reflectance prior. We first introduce the nighttime hazy imaging model, which includes a local ambient illumination item in both direct attenuation term and scattering term. Then, we propose a simple but effective image prior, maximum reflectance prior, to estimate the varying ambient illumination. The maximum reflectance prior is based on a key observation: for most daytime haze-free image patches, each color channel has very high intensity at some pixels. For the nighttime haze image, the local maximum intensities at each color channel are mainly contributed by the ambient illumination. Therefore, we can directly estimate the ambient illumination and transmission map, and consequently restore a high quality haze-free image. Experimental results on various nighttime hazy images demonstrate the effectiveness of the proposed approach. In particular, our approach has the advantage of computational efficiency, which is 10-100 times faster than state-of-the-art methods.

Underwater stereo image enhancement using a new physical model

Stereo image applications are becoming more and more prevalent. However, there has been little research on stereo image enhancement. In this paper, we address the challenging problem of underwater stereo image enhancement. A new underwater imaging model is proposed and it can better describe the degradation of underwater images including color distortion and contrast attenuation. In addition, a novel observation that the intensity of the water part within the image is mainly contributed by the scattering light is also proposed. Coupling the proposed model and prior together, the parameters of scattering light can be estimated. Then an iterative approach to process stereo matching and stereo image enhancement alternatively is presented, which can significantly improve the quality of the images and depth maps. The experimental results demonstrate that the proposed method can significantly enhance the image visibility and achieve better depth perception.

Fast depth estimation from single image using structured forest

Depth estimation from single image is an important component of many vision systems, including robot navigation, motion capture and video surveillance. In this paper, we propose to apply a structure forest framework to infer depth information from single RGB image. The core idea of our approach is to exploit the structure properties exhibit in local patches of depth map to learn the depth level for each pixel. We formulate the problem of depth estimation in a structured learning framework based on random decision forests. Each trained forest infers a patch of structured labels that are accumulated across the image to obtain the final depth map. Moreover, we systematically investigate a variety of depth-relevant features and the regression forest framework automatically determines the best feature combination and uses as input of structure forest. Our approach achieves quasi real-time performance that is orders of magnitude faster than state-of-the-art approaches, while also achieving state-of-the-art depth estimation results on the Make3D dataset.

Segmentation methods for noise level estimation and adaptive denoising from a single image

In order to significantly remove noise, many computer vision algorithms require that the image noise level is known. In this paper, we present two simple but effective methods to automatically estimate the noise level from a single image using improved adaptive graph-based segmentation. The first method can estimate the noise standard deviation of image contaminated by Gaussian noise or natural noise. The second method is based on point-wise estimation of the image noise. Both of them can be applied to attenuate real noise produced by CCD camera, even if the noise is inhomogeneous. The main advantage of our algorithms compared with others is its speed: its complexity is a linear function of the number of the image pixels. This speed allows noise level estimation to be applied in real-time system. At last, we illustrate the utility of the noise estimation for constant time bilateral filter. Meanwhile, experimental results demonstrate the effectiveness of our algorithms.

A Novel Segmentation-Based Video Denoising Method with Noise Level Estimation

Most of the state of the art video denoising algorithms consider additive noise model, which is often violated in practice. In this paper, two main issues are addressed, namely, segmentation-based block matching and the estimation of noise level. Different with the previous block matching methods, we present an efficient algorithm to perform the block matching in spatially-consistent segmentations of each image frame. To estimate the noise level function (NLF), which describes the noise level as a function of image brightness, we propose a fast bilateral medial filter based method. Under the assumption of short-term coherence, this estimation method is consequently extended from single frame to multi-frames. Coupling these two techniques together, we propose a segmentation-based customized BM3D method to remove colored multiplicative noise for videos. Experimental results on benchmark data sets and real videos show that our method significantly outperforms the state of the art in removing the colored multiplicative noise.