Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 5 de 5
Mais filtros

Base de dados
Intervalo de ano de publicação
IEEE Trans Cybern ; 2020 Jan 13.
Artigo em Inglês | MEDLINE | ID: mdl-31940575


Reflection caused by glass often degrades the quality of an image and further makes it difficult to estimate depth. In this article, we propose joint reflection removal and depth estimation from a single image. We perform reflection removal (transmission recovery) and depth estimation jointly using a collaborative neural network that consists of four blocks: 1) encoder for feature extraction; 2) reflection removal subnetwork (RRN); 3) depth estimation subnetwork (DEN); and 4) depth refinement guided by the transmission layer. We achieve collaboration between reflection removal and depth estimation by concatenating intermediate features of DEN with RRN. Since the recovered transmission layer contains accurate edges of objects behind glass, we refine the estimated depth with its guidance by guided image filtering. The experimental results demonstrate that the proposed method achieves both reflection removal and depth estimation even for images with dominant reflections. Besides, this article offers a new way of treating reflections in images to introduce depth estimation into reflection removal and achieve reflection removal and depth estimation simultaneously.

IEEE Trans Image Process ; 28(4): 1625-1635, 2019 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-30346286


Dilated convolutions support expanding receptive field without parameter exploration or resolution loss, which turn out to be suitable for pixel-level prediction problems. In this paper, we propose multiscale single image super-resolution (SR) based on dilated convolutions. We adopt dilated convolutions to expand the receptive field size without incurring additional computational complexity. We mix standard convolutions and dilated convolutions in each layer, called mixed convolutions, i.e., in the mixed convolutional layer, and the feature extracted by dilated convolutions and standard convolutions are concatenated. We theoretically analyze the receptive field and intensity of mixed convolutions to discover their role in SR. Mixed convolutions remove blind spots and capture the correlation between low-resolution (LR) and high-resolution (HR) image pairs successfully, thus achieving good generalization ability. We verify those properties of mixed convolutions by training 5-layer and 10-layer networks. We also train a 20-layer deep network to compare the performance of the proposed method with those of the state-of-the-art ones. Moreover, we jointly learn maps with different scales from a LR image to its HR one in a single network. Experimental results demonstrate that the proposed method outperforms the state-of-the-art ones in terms of PSNR and SSIM, especially for a large-scale factor.

Artigo em Inglês | MEDLINE | ID: mdl-30418902


When people take a picture through glass, the scene behind the glass is often interfered by specular reflection. Due to relatively easy implementation, most studies have tried to recover the transmitted scene from multiple images rather than single image. However, the use of multiple images is not practical for common users in real situations due to the critical shooting conditions. In this paper, we propose single image reflection removal using convolutional neural networks. We provide a ghosting model that causes reflection effects in captured images. First, we synthesize multiple reflection images from the input single one based on ghosting model and relative intensity. Then, we construct an end-to-end network that consists of encoder and decoder. To optimize the network parameters, we use a joint training strategy to learn the layer separation knowledge from the synthesized reflection images. For the loss function, we utilize both internal and external losses in optimization. Finally, we apply the proposed network to single image reflection removal. Compared with the previous work, the proposed method does not need handcrafted features and specular filters for reflection removal. Experimental results show that the proposed method successfully removes reflection from both synthetic and real images as well as achieves the highest scores in PSNR, SSIM and FSIM.

IEEE Trans Image Process ; 25(3): 1301-11, 2016 Mar.
Artigo em Inglês | MEDLINE | ID: mdl-26780795


In this paper, we propose interactive image segmentation using adaptive constraint propagation (ACP), called ACP Cut. In interactive image segmentation, the interactive inputs provided by users play an important role in guiding image segmentation. However, these simple inputs often cause bias that leads to failure in preserving object boundaries. To effectively use this limited interactive information, we employ ACP for semisupervised kernel matrix learning which adaptively propagates the interactive information into the whole image, while successfully keeping the original data coherence. Moreover, ACP Cut adopts seed propagation to achieve discriminative structure learning and reduce the computational complexity. Experimental results demonstrate that the ACP Cut extracts foreground objects successfully from the background and outperforms the state-of-the-art methods for interactive image segmentation in terms of both effectiveness and efficiency.

Opt Express ; 18(7): 7138-49, 2010 Mar 29.
Artigo em Inglês | MEDLINE | ID: mdl-20389735


This paper provides a novel Bayesian deringing method to reduce ringing artifacts caused by image interpolation and JPEG compression. To remove the ringing artifacts, the proposed method uses a Bayesian framework based on a SGLI (spatial-gradient-local-inhomogeneity) prior. The SGLI prior employs two complementary discontinuity measures: spatial gradient and local inhomogeniety. The spatial gradient measure effectively detects strong edge components in images. In addition, the local inhomogeniety measure successfully detects locations of the significant discontinuities by taking uniformity of small regions into consideration. The two complementary measures are elaborately combined to create prior probabilities of the Bayesian deringing framework. Thus, the proposed deringing method can effectively preserve the significant discontinuities such as textures of objects as well as the strong edge components in images while reducing the ringing artifacts. Experimental results show that the proposed deringing method achieves average PSNR gains of 0.09 dB in image interpolation artifact reduction and 0.21 dB in JPEG compression artifact reduction.

Processamento de Imagem Assistida por Computador/métodos , Processamento de Sinais Assistido por Computador , Algoritmos , Artefatos , Teorema de Bayes , Gráficos por Computador , Simulação por Computador , Compressão de Dados/métodos , Humanos , Modelos Estatísticos , Óptica e Fotônica