Image Colorization Using the Global Scene-Context Style and Pixel-Wise Semantic Segmentation

Nguyen-Quynh, Tram-Tran; Kim, Soo-Hyung; Do, Nhu-Tai

doi:10.1109/access.2020.3040737

Cited by 13 publications

(6 citation statements)

References 30 publications

(72 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They use a GAN encoder to first find matching features that are similar to exemplars, and after that modulate these features into the colorization process. Using both global and local priors, Nguyen-Quynh et al [38] suggested an encoder-decoder image colorization model. By using picture detection, they hone low-level encoding features for the global priors.…”

Section: Learning-based Colorizationmentioning

confidence: 99%

An Improved Encoder-Decoder CNN with Region-Based Filtering for Vibrant Colorization

Gain¹,

Rahman²,

Debnath³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Colorization is the practice of adding appropriate chromatic values to monochrome photographs or videos. A real-valued luminance image can be mapped to a three-dimensional color image. However, it is a severely ill-defined problem and not has a single solution. In this paper, an encoder-decoder Convolutional Neural Network (CNN) model is used for colorizing gray images where the encoder is a Densely Connected Convolutional Network (DenseNet) and the decoder is a conventional CNN. The DenseNet extracts image features from gray images and the conventional CNN outputs a * b * color channels. Due to a large number of desaturated color components compared to saturated color components in the training images, the saturated color components have a strong tendency towards desaturated color components in the predicted a * b * channel. To solve the problems, we rebalance the predicted a * b * color channel by smoothing every subregion individually using the average filter. 2 stage k-means clustering technique is applied to divide the subregions. Then we apply Gamma transformation in the entire a * b * channel to saturate the image. We compare our proposed method with several existing methods. From the experimental results, we see that our proposed method has made some notable improvements over the existing methods and color representation of gray-scale images by our proposed method is more plausible to visualize. Additionally, our suggested approach beats other approaches in terms of Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM) and Histogram.

show abstract

Section: Learning-based Colorizationmentioning

confidence: 99%

An Improved Encoder-Decoder CNN with Region-Based Filtering for Vibrant Colorization

Gain¹,

Rahman²,

Debnath³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…They used a GAN encoder to first find matching features that are similar to exemplars, and after that modulate these features into the colorization process. Nguyen-Quynh et al [37] suggested an encoder-decoder image colorization model by exploiting both global and local priors. Bahng et.…”

Section: B Related Workmentioning

confidence: 99%

A Novel Unbiased Deep Learning Approach (DL-Net) in Feature Space for Converting Gray to Color Image

Gain

Debnath

2023

IEEE Access

View full text Add to dashboard Cite

Gray to Color conversion causes difficulties because of the nature of its intrinsic multimodality. Despite recent significant advancements in this domain by numerous learning-based approaches, there still have two drawbacks: i) implausible color assignment and ii) contextual ambiguity. Recently deep learning models are being used for colorization as they outperform others. In a training image, desaturated color components are greater than saturated color components due to the larger background areas (clouds, pavement, dirt, walls, etc.) compared to the focused objects. This imbalanced feature representation biases the learning model in favor of major features. However, small regions with specific colors are the region of interest. To solve this problem, we proposed the Deep Localization Network (DL-Net) by modifying the mean squared error backpropagation algorithm. We compute chromatic component-based Local Losses (LLs) which are the primary component of the proposed DL-Net. The LL employs priority on rare semantic components of the original image features. It works to improve diverse-range dependency modeling in an effort to reduce contextual ambiguity and color leakage that promotes the production of more plausible coloring. With a number of current methodologies, we contrast our proposed approach. The experimental findings demonstrate that our proposed method produces good colorization of images and outperforms other methods in terms of SSIM, MSE, and PSNR quality criteria.

show abstract

“…Another study proposed a label smoothing approach to improve the model uncertainty calibration for scene segmentation [33]. In the context of image colorization, one study used label smoothing to achieve more accurate scene segmentation [34]. However, none of these studies have properly addressed the spatially-varying nature of boundary uncertainty in semantic segmentation.…”

Section: B Segmentation With Noisy Labelsmentioning

confidence: 99%

Learning to segment fetal brain tissue from noisy annotations

Karimi¹,

Rollins²,

Velasco‐Annis³

et al. 2022

Preprint

View full text Add to dashboard Cite

Automatic fetal brain tissue segmentation can enhance the quantitative assessment of brain development at this critical stage. Deep learning methods represent the state of the art in medical image segmentation and have also achieved impressive results in brain segmentation. However, effective training of a deep learning model to perform this task requires a large number of training images to represent the rapid development of the transient fetal brain structures. On the other hand, manual multilabel segmentation of a large number of 3D images is prohibitive.To address this challenge, we segmented 272 training images, covering 19-39 gestational weeks, using an automatic multiatlas segmentation strategy based on deformable registration and probabilistic atlas fusion, and manually corrected large errors in those segmentations. Since this process generated a large training dataset with noisy segmentations, we developed a novel label smoothing procedure and a loss function to train a deep learning model with smoothed noisy segmentations. Our proposed methods properly account for the uncertainty in tissue boundaries. We evaluated our method on 23 manually-segmented test images of a separate set of fetuses. Results show that our method achieves an average Dice similarity coefficient of 0.893 and 0.916 for the transient structures of younger and older fetuses, respectively. Our method generated results that were significantly more accurate than several state-of-the-art methods including nnU-Net that achieved the closest results to our method. Our trained model can serve as a valuable tool to enhance the accuracy and reproducibility of fetal brain analysis in MRI.

show abstract

Image Colorization Using the Global Scene-Context Style and Pixel-Wise Semantic Segmentation

Cited by 13 publications

References 30 publications

An Improved Encoder-Decoder CNN with Region-Based Filtering for Vibrant Colorization

An Improved Encoder-Decoder CNN with Region-Based Filtering for Vibrant Colorization

A Novel Unbiased Deep Learning Approach (DL-Net) in Feature Space for Converting Gray to Color Image

Learning to segment fetal brain tissue from noisy annotations

Contact Info

Product

Resources

About