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.

Visual salience and stack extension based ghost removal for high-dynamic-range imaging

Abstract: High-dynamic-range imaging (HDRI) techniques are proposed to extend the dynamic range of captured images against sensor limitation. The key issue of multi-exposure fusion in HDRI is removing ghost artifacts caused by motion of moving objects and handheld cameras. This paper proposes a ghost-free HDRI algorithm based on visual salience and stack extension. To improve the accuracy of ghost areas detection, visual salience based bilateral motion detection is introduced to measure image differences. For exposure fusion, the proposed algorithm reduces brightness discontinuity and enhances details by stack extension, and rejects the information of ghost areas to avoid artifacts via fusion masks. Experiment results show that the proposed algorithm can remove ghost artifacts accurately for both static and handheld cameras, remain robust to scenes with complex motion and keep low complexity over recent advances including patch based method and rank minimization based method by 20.4% and 63.6% time savings on average.

Mixing tone mapping operators on the GPU by differential zone mapping based on psychophysical experiments

Abstract: In this paper, we present a new technique for displaying High Dynamic Range (HDR) images on Low Dynamic Range (LDR) displays in an efficient way on the GPU. The described process has three stages. First, the input image is segmented into luminance zones. Second, the tone mapping operator (TMO) that performs better in each zone is automatically selected. Finally, the resulting tone mapping (TM) outputs for each zone are merged, generating the final LDR output image. To establish the TMO that performs better in each luminance zone we conducted a preliminary psychophysical experiment using a set of HDR images and six different TMOs. We validated our composite technique on several (new) HDR images and conducted a further psychophysical experiment, using an HDR display as the reference that establishes the advantages of our hybrid three-stage approach over a traditional individual TMO. Finally, we present a GPU version, which is perceptually equal to the standard version but with much improved computational performance.

Tone mapping high dynamic range images based on region-adaptive self-supervised deep learning

Abstract: This paper presents a region-adaptive self-supervised deep learning (RASSDL) technique for high dynamic range (HDR) image tone mapping. The RASSDL tone mapping operator (TMO) is a convolutional neural network (CNN) trained on local image regions that can seamlessly tone map images of arbitrary sizes. The training of RASSDL TMO is through the design of a self-supervising target that automatically adapts to the local image regions based on their information contents. The self-supervising target is designed to ensure the tone-mapped output achieves a balance between preserving the relative contrast of the original scene and the visibilities of the fine details to achieve faithful reproduction of the HDR scene. Distinguishing from many existing TMOs that require manual tuning of parameters, RASSDL is parameter-free and completely automatic. Experimental results demonstrate that RASSDL TMO can achieve state-of-the-art performance in terms of preserving overall contrasts, revealing fine details, and being free from visual artifacts.

High Dynamic Range Imaging On Digital Still Camera

Abstract: Film photographers had used to "dodge and burn" to express a greater dynamic range than original photographic paper. The greater dynamic range imaging is a big challenge on general digital camera area. In this paper, we propose a solution to generate a high dynamic range (HDR) image on a digital still camera, considering a minimum resource and a variable dynamic range capturing. Our approach consists of three parts: scene capturing, HDR image generation and DR compression. The scene capturing needs an adaptive controlling of the exposure time during multiple captures. The HDR image generation from multiple captured images has to preserve and combine the captured dynamic range data for storage and display having low dynamic range (LDR). Our research is implemented onto a commercialized camera system and is evaluated by the maximum capturing dynamic range and the HDR image quality.

Systems and methods for high-dynamic range imaging

Abstract: Aspects of the present disclosure relate to systems and methods for generating High-Dynamic Range (HDR) images. An example device may include a camera, one or more processors, and a memory. The memory may include instructions that, when executed by the one or more processors, cause the device to determine, from a preview image captured with an initial exposure value by a camera, a first exposure value for capturing a reference image, and a second exposure value for capturing a first non-reference image, wherein the second exposure value is based on a difference between the initial exposure value and the first exposure value. Execution of the instructions may further cause the device to capture the reference image using the first exposure value, capture the first non-reference image using the second exposure value, and blend the reference image and the first non-reference image in generating an HDR image.