Natural Image Matting Using Deep Convolutional Neural Networks

Cho, Donghyeon; Tai, Yu-Wing; Kweon, In-So

doi:10.1007/978-3-319-46475-6_39

Cited by 155 publications

(140 citation statements)

References 30 publications

Supporting

Mentioning

140

Contrasting

Order By: Relevance

“…Their method first employs a deep neural network to generate the trimap of a portrait image and then feeds it to an offthe-shelf matting method, namely the Closed-form Matting algorithm [27], to obtain the final matting result. Cho et al developed a deep matting method that takes the matting results from the Closed-form Matting algorithm [27] and the KNN Matting algorithm [6] as input, and refine it using a deep neural network [8,9]. Xu et al developed a large-scale synthetic image matting dataset and used it to train a twostage deep neural network for alpha matting.…”

Section: Related Workmentioning

confidence: 99%

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Hou

Liu

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

158

166

View full text Add to dashboard Cite

Natural image matting is an important problem in computer vision and graphics. It is an ill-posed problem when only an input image is available without any external information. While the recent deep learning approaches have shown promising results, they only estimate the alpha matte. This paper presents a context-aware natural image matting method for simultaneous foreground and alpha matte estimation. Our method employs two encoder networks to extract essential information for matting. Particularly, we use a matting encoder to learn local features and a context encoder to obtain more global context information. We concatenate the outputs from these two encoders and feed them into decoder networks to simultaneously estimate the foreground and alpha matte. To train this whole deep neural network, we employ both the standard Laplacian loss and the feature loss: the former helps to achieve high numerical performance while the latter leads to more perceptually plausible results. We also report several data augmentation strategies that greatly improve the network's generalization performance. Our qualitative and quantitative experiments show that our method enables high-quality matting for a single natural image. Our inference codes and models have been made publicly available at https://github. com/hqqxyy/Context-Aware-Matting.

show abstract

Section: Related Workmentioning

confidence: 99%

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Hou

Liu

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

158

166

View full text Add to dashboard Cite

show abstract

“…For the Composition-1k test set, we evaluate 6 recent state-of-the-art methods, namely Closed Form [21], KNN [7], DCNN [9], Information Flow [1], AlphaGAN [24], and Deep Image Matting [38]. The quantitative results under the Grad, SAD and MSE are shown in Table 2.…”

Section: Results On Composition-1kmentioning

confidence: 99%

“…Recently, deep learning has shown impressive performance on various computer vision tasks including image matting. Cho et al [9] proposed an end-to-end architecture named DCNN that utilizes the results of closed-form matting [21] and KNN matting [7] to predict better alpha mattes. Shen et al [29] proposed a fully automatic matting system for portrait photos based on end-to-end CNNs.…”

Section: Related Workmentioning

confidence: 99%

Disentangled Image Matting

Cai¹,

Zhang²,

Fan³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

130

116

View full text Add to dashboard Cite

Most previous image matting methods require a roughlyspecificed trimap as input, and estimate fractional alpha values for all pixels that are in the unknown region of the trimap. In this paper, we argue that directly estimating the alpha matte from a coarse trimap is a major limitation of previous methods, as this practice tries to address two difficult and inherently different problems at the same time: identifying true blending pixels inside the trimap region, and estimate accurate alpha values for them. We propose AdaMatting, a new end-to-end matting framework that disentangles this problem into two sub-tasks: trimap adaptation and alpha estimation. Trimap adaptation is a pixelwise classification problem that infers the global structure of the input image by identifying definite foreground, background, and semi-transparent image regions. Alpha estimation is a regression problem that calculates the opacity value of each blended pixel. Our method separately handles these two sub-tasks within a single deep convolutional neural network (CNN). Extensive experiments show that AdaMatting has additional structure awareness and trimap fault-tolerance. Our method achieves the state-ofthe-art performance on Adobe Composition-1k dataset both qualitatively and quantitatively. It is also the current bestperforming method on the alphamatting.com online evaluation for all commonly-used metrics.

show abstract

“…Schuler et al [39] train a multi-layer perceptron to perform image deconvolution task and obtain satisfactory results. Cho et al [6] applies CNN on image matting. And Shen et al [40] focus on portrait matting.…”

Section: Related Workmentioning

confidence: 99%

Single Image Dehazing Using Ranking Convolutional Neural Network

Song

Wang

et al. 2018

IEEE Trans. Multimedia

134

View full text Add to dashboard Cite

Single image dehazing, which aims to recover the clear image solely from an input hazy or foggy image, is a challenging ill-posed problem. Analysing existing approaches, the common key step is to estimate the haze density of each pixel. To this end, various approaches often heuristically designed haze-relevant features. Several recent works also automatically learn the features via directly exploiting Convolutional Neural Networks (CNN). However, it may be insufficient to fully capture the intrinsic attributes of hazy images. To obtain effective features for single image dehazing, this paper presents a novel Ranking Convolutional Neural Network (Ranking-CNN). In Ranking-CNN, a novel ranking layer is proposed to extend the structure of CNN so that the statistical and structural attributes of hazy images can be simultaneously captured. By training Ranking-CNN in a well-designed manner, powerful haze-relevant features can be automatically learned from massive hazy image patches. Based on these features, haze can be effectively removed by using a haze density prediction model trained through the random forest regression. Experimental results show that our approach outperforms several previous dehazing approaches on synthetic and real-world benchmark images. Comprehensive analyses are also conducted to interpret the proposed Ranking-CNN from both the theoretical and experimental aspects.

show abstract

Natural Image Matting Using Deep Convolutional Neural Networks

Cited by 155 publications

References 30 publications

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Disentangled Image Matting

Single Image Dehazing Using Ranking Convolutional Neural Network

Contact Info

Product

Resources

About