Deep Automatic Portrait Matting

Shen, Xiaoyong; Xin, Tao; Gao, Hongyun; Zhou, Chao; Jia, Jiaya

doi:10.1007/978-3-319-46448-0_6

Cited by 222 publications

(227 citation statements)

References 23 publications

Supporting

Mentioning

226

Contrasting

Unclassified

Order By: Relevance

“…Our work is most relevant to the recent deep learning approaches to image matting. Shen et al trained a dedicated deep convolutional neural network for portrait matting [43]. 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.…”

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

“…[3] first introduced the Gestalt laws to the matting problem, making more robust trimap generation possible. More recently, [6,29] utilized neural networks to generate trimaps, greatly improving the matting performances.…”

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

“…Different from existing works, our DeepGLR framework constructs neighbor-hood graphs from the CNN outputs, i.e., our graphs are built in a data-driven manner, which learns the appropriate graph connectivity for restoration directly. In [38,4], the authors also formulate graph Laplacian regularization in a deep learning pipeline; yet unlike ours, their graph constructions are fixed functions, i.e., they are not data-driven.…”

Section: Related Workmentioning

confidence: 99%

Deep Graph Laplacian Regularization for Robust Denoising of Real Images

Zeng¹,

Pang²,

Sun³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Recent developments in deep learning have revolutionized the paradigm of image restoration. However, its applications on real image denoising are still limited, due to its sensitivity to training data and the complex nature of real image noise. In this work, we combine the robustness merit of model-based approaches and the learning power of data-driven approaches for real image denoising. Specifically, by integrating graph Laplacian regularization as a trainable module into a deep learning framework, we are less susceptible to overfitting than pure CNNbased approaches, achieving higher robustness to small datasets and cross-domain denoising. First, a sparse neighborhood graph is built from the output of a convolutional neural network (CNN). Then the image is restored by solving an unconstrained quadratic programming problem, using a corresponding graph Laplacian regularizer as a prior term. The proposed restoration pipeline is fully differentiable and hence can be end-to-end trained. Experimental results demonstrate that our work is less prone to overfitting given small training data. It is also endowed with strong cross-domain generalization power, outperforming the state-of-the-art approaches by a remarkable margin.

show abstract

Deep Automatic Portrait Matting

Cited by 222 publications

References 23 publications

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Disentangled Image Matting

Deep Graph Laplacian Regularization for Robust Denoising of Real Images

Contact Info

Product

Resources

About