Explore the vast range of titles available.

Inverse Tone Mapping (ITM) methods attempt to reconstruct High Dynamic Range (HDR) information from Low Dynamic Range (LDR) image content. The dynamic range of well-exposed areas must be expanded and any missing information due to over/under-exposure must be recovered (hallucinated). The majority of methods focus on the former and are relatively successful, while most attempts on the latter are not of sufficient quality, even ones based on Convolutional Neural Networks (CNNs). A major factor for the reduced inpainting quality in some works is the choice of loss function. Work based on Generative Adversarial Networks (GANs) shows promising results for image synthesis and LDR inpainting, suggesting that GAN losses can improve inverse tone mapping results. This work presents a GAN-based method that hallucinates missing information from badly exposed areas in LDR images and compares its efficacy with alternative variations. The proposed method is quantitatively competitive with state-of-the-art inverse tone mapping methods, providing good dynamic range expansion for well-exposed areas and plausible hallucinations for saturated and under-exposed areas. A density-based normalisation method, targeted for HDR content, is also proposed, as well as an HDR data augmentation method targeted for HDR hallucination.

Sheet metal stamping is widely used for high-volume production. Despite the wide adoption, it can lead to defects in the manufactured components, making their quality unacceptable. Because of the variety of defects that can occur on the final product, human inspectors are frequently employed to detect them. However, they can be unreliable and costly, particularly at speeds that match the stamping rate. In this paper, we propose an automatic inspection framework for the stamping process that is based on computer vision and deep learning techniques. The low cost, remote sensing capability and simple implementation mean that it can be easily deployed in an industrial setting. A particular focus of this research is to account for the harsh lighting conditions and the highly reflective nature of products found in manufacturing environments that affect optical sensing techniques by making it difficult to capture the details of a scene. High dynamic range images can capture details of an environment in harsh lighting conditions, and in the context of this work, can capture highly reflective metals found in sheet metal stamping manufacturing. Building on this imaging technique, we propose a framework including a deep learning model to detect defects in sheet metal stamping parts. To test the framework, sheet metal ‘Nakajima’ samples were pressed with an industrial stamping press. Then optimally exposed, sequence of exposures, tone-mapped and high dynamic range images of the samples were used to train convolutional neural network-based detectors. Analysis of the resulting models showed that high dynamic range image-based models achieved substantially higher accuracy and minimal false-positive predictions.

High dynamic range (HDR) displays based on liquid crystal panels require local dimming algorithms to reproduce content with high fidelity and HDR. However, most local dimming algorithms are developed by using hand-crafted features and most of them focus on low dynamic range images rather than HDR images. In addition, few local dimming algorithms can manage well the conflicting requirements of maintaining image quality while minimising power consumption. In this paper, we propose a genetic algorithm for backlight local dimming (GABLD) that generates images for the HDR display based on the given fitness function and the HDR content about to be displayed while considering the impact of power consumption and image quality. The effectiveness of the GABLD method is demonstrated in three aspects: the fidelity of reconstruction of HDR images, the power consumption, and the visualisation of HDR content on HDR displays. The results show that the proposed method has good performance in terms of both the image quality and power consumption, and it retains more details especially for areas with highlights when compared to traditional methods.

High Dynamic Range (HDR) imaging enables us to capture, manipulate and reproduce real world lighting with high fidelity. HDR displays are becoming more common, however, most content, from over 100 years of media, is Low Dynamic Range (LDR). Dynamic range expansion methods generate HDR from LDR content, for displaying on HDR displays and various other applications, attempting to recover missing information from the original HDR signal that is lost due to saturation or quantisation. Multiple methods have been proposed, addressing different aspects of the problem, however most are model-driven and require adjustment of parameters which may also vary depending on the content. This thesis proposes using Convolutional Neural Networks (CNNs) for fully data-driven, end-to-end dynamic range expansion. A novel multibranch CNN termed ExpandNet is proposed that processes LDR inputs on multiple scales without using upsampling layers, which have been observed to cause artefacts when used in other traditional CNNs, in particular the UNet architecture. ExpandNet is evaluated and compared against traditional methods including other CNNs and is found to outperform all other methods on multiple metrics. An investigation of the effect of upsampling layers on the spectrum of the network outputs is then presented, characterising their impact in the Fourier domain, providing a way to assess the structural biases of CNNs. A new upsampling module is then proposed, based on the Guided Image Filter that provides spectrally consistent outputs when used in a UNet architecture, forming the Guided UNet (GUNet). The GUNet architecture is evaluated similarly to ExpandNet and is found to perform well, while executing faster and consuming less memory than ExpandNet. Finally, multiple methods using Generative Adversarial Networks (GAN) are proposed and evaluated, that hallucinate content in badly-exposed areas of the input while simultaneously expanding the range of the well-exposed areas. A single network configuration based on UNet, termed L-GAN, produces better results qualitatively and also performs well quantitatively compared to state-of-the-art methods such as ExpandNet and GUNet.

Inverse Tone Mapping (ITM) methods attempt to reconstruct High Dynamic Range (HDR) information from Low Dynamic Range (LDR) image content. The dynamic range of well-exposed areas must be expanded and any missing information due to over/under-exposure must be recovered (hallucinated). The majority of methods focus on the former and are relatively successful, while most attempts on the latter are not of sufficient quality, even ones based on Convolutional Neural Networks (CNNs). A major factor for the reduced inpainting quality in some works is the choice of loss function. Work based on Generative Adversarial Networks (GANs) shows promising results for image synthesis and LDR inpainting, suggesting that GAN losses can improve inverse tone mapping results. This work presents a GAN-based method that hallucinates missing information from badly exposed areas in LDR images and compares its efficacy with alternative variations. The proposed method is quantitatively competitive with state-of-the-art inverse tone mapping methods, providing good dynamic range expansion for well-exposed areas and plausible hallucinations for saturated and under-exposed areas. A density-based normalisation method, targeted for HDR content, is also proposed, as well as an HDR data augmentation method targeted for HDR hallucination.

Convolutional Neural Networks (CNNs) are the current de-facto models used for many imaging tasks due to their high learning capacity as well as their architectural qualities. The ubiquitous UNet architecture provides an efficient and multi-scale solution that combines local and global information. Despite the success of UNet architectures, the use of upsampling layers can cause artefacts. In this work, a method for assessing the structural biases of UNets and the effects these have on the outputs is presented, characterising their impact in the Fourier domain. A new upsampling module is proposed, based on a novel use of the Guided Image Filter, that provides spectrally consistent outputs when used in a UNet architecture, forming the Guided UNet (GUNet). The GUNet architecture is applied and evaluated for example applications of inverse tone mapping/dynamic range expansion and colourisation from grey-scale images and is shown to provide higher fidelity outputs.

Recently, Deep Learning-based methods for inverse tone-mapping standard dynamic range (SDR) images to obtain high dynamic range (HDR) images have become very popular. These methods manage to fill over-exposed areas convincingly both in terms of details and dynamic range. Typically, these methods, to be effective, need to learn from large datasets and to transfer this knowledge to the network weights. In this work, we tackle this problem from a completely different perspective. What can we learn from a single SDR video? With the presented zero-shot approach, we show that, in many cases, a single SDR video is sufficient to be able to generate an HDR video of the same quality or better than other state-of-the-art methods.

Dual-panel displays require local dimming algorithms in order to reproduce content with high fidelity and high dynamic range. In this work, a novel deep learning based local dimming method is proposed for rendering HDR images on dual-panel HDR displays. The method uses a Convolutional Neural Network to predict backlight values, using as input the HDR image that is to be displayed. The model is designed and trained via a controllable power parameter that allows a user to trade off between power and quality. The proposed method is evaluated against six other methods on a test set of 105 HDR images, using a variety of quantitative quality metrics. Results demonstrate improved display quality and better power consumption when using the proposed method compared to the best alternatives.

High dynamic range (HDR) imaging provides the capability of handling real world lighting as opposed to the traditional low dynamic range (LDR) which struggles to accurately represent images with higher dynamic range. However, most imaging content is still available only in LDR. This paper presents a method for generating HDR content from LDR content based on deep Convolutional Neural Networks (CNNs) termed ExpandNet. ExpandNet accepts LDR images as input and generates images with an expanded range in an end-to-end fashion. The model attempts to reconstruct missing information that was lost from the original signal due to quantization, clipping, tone mapping or gamma correction. The added information is reconstructed from learned features, as the network is trained in a supervised fashion using a dataset of HDR images. The approach is fully automatic and data driven; it does not require any heuristics or human expertise. ExpandNet uses a multiscale architecture which avoids the use of upsampling layers to improve image quality. The method performs well compared to expansion/inverse tone mapping operators quantitatively on multiple metrics, even for badly exposed inputs.