High-dynamic-range imaging

About: High-dynamic-range imaging is a research topic. Over the lifetime, 766 publications have been published within this topic receiving 22577 citations.

Deep Recursive HDRI: Inverse Tone Mapping using Generative Adversarial Networks

Abstract: High dynamic range images contain luminance information of the physical world and provide more realistic experience than conventional low dynamic range images. Because most images have a low dynamic range, recovering the lost dynamic range from a single low dynamic range image is still prevalent. We propose a novel method for restoring the lost dynamic range from a single low dynamic range image through a deep neural network. The proposed method is the first framework to create high dynamic range images based on the estimated multi-exposure stack using the conditional generative adversarial network structure. In this architecture, we train the network by setting an objective function that is a combination of L1 loss and generative adversarial network loss. In addition, this architecture has a simplified structure than the existing networks. In the experimental results, the proposed network generated a multi-exposure stack consisting of realistic images with varying exposure values while avoiding artifacts on public benchmarks, compared with the existing methods. In addition, both the multi-exposure stacks and high dynamic range images estimated by the proposed method are significantly similar to the ground truth than other state-of-the-art algorithms.

Convolutional Sparse Coding for High Dynamic Range Imaging

Abstract: Current HDR acquisition techniques are based on either i fusing multibracketed, low dynamic range LDR images, ii modifying existing hardware and capturing different exposures simultaneously with multiple sensors, or iii reconstructing a single image with spatially-varying pixel exposures. In this paper, we propose a novel algorithm to recover high-quality HDRI images from a single, coded exposure. The proposed reconstruction method builds on recently-introduced ideas of convolutional sparse coding CSC; this paper demonstrates how to make CSC practical for HDR imaging. We demonstrate that the proposed algorithm achieves higher-quality reconstructions than alternative methods, we evaluate optical coding schemes, analyze algorithmic parameters, and build a prototype coded HDR camera that demonstrates the utility of convolutional sparse HDRI coding with a custom hardware platform.

Single image HDR reconstruction using a CNN with masked features and perceptual loss

Abstract: Digital cameras can only capture a limited range of real-world scenes' luminance, producing images with saturated pixels. Existing single image high dynamic range (HDR) reconstruction methods attempt to expand the range of luminance, but are not able to hallucinate plausible textures, producing results with artifacts in the saturated areas. In this paper, we present a novel learning-based approach to reconstruct an HDR image by recovering the saturated pixels of an input LDR image in a visually pleasing way. Previous deep learning-based methods apply the same convolutional filters on wellexposed and saturated pixels, creating ambiguity during training and leading to checkerboard and halo artifacts. To overcome this problem, we propose a feature masking mechanism that reduces the contribution of the features from the saturated areas. Moreover, we adapt the VGG-based perceptual loss function to our application to be able to synthesize visually pleasing textures. Since the number of HDR images for training is limited, we propose to train our system in two stages. Specifically, we first train our system on a large number of images for image inpainting task and then fine-tune it on HDR reconstruction. Since most of the HDR examples contain smooth regions that are simple to reconstruct, we propose a sampling strategy to select challenging training patches during the HDR fine-tuning stage. We demonstrate through experimental results that our approach can reconstruct visually pleasing HDR results, better than the current state of the art on a wide range of scenes.

Method to extend laser depth map range

Abstract: A method for extending the dynamic range of a depth map by deriving depth information from a synthesized image of a plurality of images captured at different light intensity levels and/or captured over different sensor integration times is described. In some embodiments, an initial image of an environment is captured while the environment is illuminated with light of a first light intensity. One or more subsequent images are subsequently captured while the environment is illuminated with light of one or more different light intensities. The one or more different light intensities may be dynamically configured based on a degree of pixel saturation associated with previously captured images. The initial image and the one or more subsequent images may be synthesized into a synthesized image by applying high dynamic range imaging techniques.

Systems and Methods for High Dynamic Range Imaging Using Array Cameras

Abstract: Systems and methods for high dynamic range imaging using array cameras in accordance with embodiments of the invention are disclosed. In one embodiment of the invention, a method of generating a high dynamic range image using an array camera includes defining at least two subsets of active cameras, determining image capture settings for each subset of active cameras, where the image capture settings include at least two exposure settings, configuring the active cameras using the determined image capture settings for each subset, capturing image data using the active cameras, synthesizing an image for each of the at least two subset of active cameras using the captured image data, and generating a high dynamic range image using the synthesized images.