A Learned Representation of Artist-Specific Colourisation

Noord, Nanne van; Postma, Eric

doi:10.1109/iccvw.2017.343

Cited by 8 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The upscaling procedure is identical for both branches; after several trials with different methodologies, such as transposed convolutions [51], bi-linear resizing and nearest-neighbor upsampling [52], we adopted a sub-pixel convolution layer as explained in detail in [53]. So, for either branch, the last 2D or 3D convolution generates s 2 •C features in order to produce the final tensors of shape sH × sW × C for the residual sum.…”

Section: A Network Architecturementioning

confidence: 99%

Multi-Image Super Resolution of Remotely Sensed Images Using Residual Attention Deep Neural Networks

et al. 2020

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) consistently proved state-of-the-art results in image Super-resolution (SR), representing an exceptional opportunity for the remote sensing field to extract further information and knowledge from captured data. However, most of the works published in the literature focused on the Single-image Super-resolution problem so far. At present, satellite-based remote sensing platforms offer huge data availability with high temporal resolution and low spatial resolution. In this context, the presented research proposes a novel residual attention model (RAMS) that efficiently tackles the Multi-image Super-resolution task, simultaneously exploiting spatial and temporal correlations to combine multiple images. We introduce the mechanism of visual feature attention with 3D convolutions in order to obtain an aware data fusion and information extraction of the multiple low-resolution images, transcending limitations of the local region of convolutional operations. Moreover, having multiple inputs with the same scene, our representation learning network makes extensive use of nestled residual connections to let flow redundant low-frequency signals and focus the computation on more important high-frequency components. Extensive experimentation and evaluations against other available solutions, either for Single or Multi-image Super-resolution, demonstrated that the proposed deep learning-based solution can be considered state-of-the-art for Multi-image Super-resolution for remote sensing applications.

show abstract

Section: A Network Architecturementioning

confidence: 99%

Multi-Image Super Resolution of Remotely Sensed Images Using Residual Attention Deep Neural Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Besides enforcing the computation of the convolutional neural features in a perceptual space, the use of L*a*b* space serves the scope of rebalancing colors, so that they fit into the overall palette of the dataset. In order to improve the color coherence, we smooth the effect of L1 loss in GANs—that of filling in empty spaces with the mean colour of the gamut, which results in inaccurate and desaturated colors—by adding a color rebalancing loss similar to [ 28 , 31 ].…”

Section: Methodsmentioning

confidence: 99%

“…The full mathematical formulation for the color rebalancing loss can be followed in Equations ( 1 )–( 4 ). The parameter p was chosen as in [ 31 ]. The weight for the losses are as follows:

.…”

Section: Methodsmentioning

confidence: 99%

Colour-Balanced Edge-Guided Digital Inpainting: Applications on Artworks

Ciortan

George

Hardeberg

2021

Sensors

View full text Add to dashboard Cite

The virtual inpainting of artworks provides a nondestructive mode of hypothesis visualization, and it is especially attractive when physical restoration raises too many methodological and ethical concerns. At the same time, in Cultural Heritage applications, the level of details in virtual reconstruction and their accuracy are crucial. We propose an inpainting algorithm that is based on generative adversarial network, with two generators: one for edges and another one for colors. The color generator rebalances chromatically the result by enforcing a loss in the discretized gamut space of the dataset. This way, our method follows the modus operandi of an artist: edges first, then color palette, and, at last, color tones. Moreover, we simulate the stochasticity of the lacunae in artworks with morphological variations of a random walk mask that recreate various degradations, including craquelure. We showcase the performance of our model on a dataset of digital images of wall paintings from the Dunhuang UNESCO heritage site. Our proposals of restored images are visually satisfactory and they are quantitatively comparable to state-of-the-art approaches.

show abstract

“…However, some classes of water have small attenuation in shallow water, such as water type I, IA, IB about 1m to 5m, which have little effect on objects. Therefore we set different depth-ranges for different water classes: set the depth-range of water 9, 7 and 5 to [1,5], set the depth-range of water 3 and 1 to [1,15] and set the depth range of water I, IA, IB, II, III to [5,20]. At the same time, we select a random global veiling-light A c ∈ [0, 1].…”

Section: Dataset Constructionmentioning

confidence: 99%

“…In [14] Odena concats a one-hot class vector with the input vector, and maximize the the loglikelihood of the real image and the log-likelihood of the correct class. In [15] the conditional instance normalization was proposed to generate images in completely different styles by fedding the generator with class- In this paper, we propose a water class embedding block (WCEB) to constrain the feature space of every class of underwater images. As shown in Figure 2, we first encode the water class into a one-hot vector.…”

Section: A Water Class Embedding Blockmentioning

confidence: 99%

CA-GAN: Class-Condition Attention GAN for Underwater Image Enhancement

Wang

Deng³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Underwater images suffer from serious color distortion and detail loss because of the wavelength-dependent light absorption and scattering, which seriously influences the subsequent underwater object detection and recognition. The latest methods for underwater image enhancement are based on deep models, which focus on finding a mapping function from the underwater image subspace to a ground-truth image subspace. They neglect the diversity of underwater conditions which leads to different background colors of underwater images. In this paper, we propose a Class-condition Attention Generative Adversarial Network (CA-GAN) to enhance an underwater image. We build an underwater image dataset which contains ten categories generated by the simulator with different water attenuation coefficient and depth. Relying on the underwater image classes, CA-GAN creates a many-to-one mapping function for an underwater image. Moreover, in order to generate the realistic image, attention mechanism is utilized. In the channel attention block, the feature maps in the front-end layers and the back-end layers are fused along channels, and in the spatial attention block, feature maps are pixel-wise fused. Extensive experiments are conducted on synthetic and real underwater images. The experimental results demonstrate that CA-GAN can effectively recover color and detail of various scenes of underwater images and is superior to the state-of-the-art methods.

show abstract

A Learned Representation of Artist-Specific Colourisation

Abstract: The colours used in a painting are determined by artists and the pigments at their disposal. Therefore

Cited by 8 publications

References 20 publications

Multi-Image Super Resolution of Remotely Sensed Images Using Residual Attention Deep Neural Networks

Multi-Image Super Resolution of Remotely Sensed Images Using Residual Attention Deep Neural Networks

Colour-Balanced Edge-Guided Digital Inpainting: Applications on Artworks

CA-GAN: Class-Condition Attention GAN for Underwater Image Enhancement

Contact Info

Product

Resources

About