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.

An Experimental Based Study on Different Sources of Noise for High Dynamic Range Imaging

Abstract: In image processing, computer graphics, and photography, high dynamic range imaging (HDRI or simply HDR) is set of techniques that allow a grater dynamic range between the lightest and darkest areas of an image than current standard digital imaging techniques or photographic methods. By fusing several low dynamic range (LDR) images together we can get a high dynamic range image. In this process we need to fuse less noisy LDR images together in order to get more pleasing output images. A detailed study on different sources of noise is carried out on this paper. They include photon shot noise, read noise, pattern noise, pixel response non-uniformity (PRNU), quantization error and thermal noise. We used a Canon DSLR camera for experimental results.

Snapshot On-chip HDR ROIC Architectures

Abstract: We describe novel digital readout integrated circuits (DROICs) that achieve snapshot on-chip high dynamic range imaging where most commercial systems require a multiple exposure acquisition.

High dynamic range (HDR) imaging for camera-in-the-loop computer-generated holography (CGH) using spatially varying pixel exposures

Abstract: A traditional limitation of holographic displays has been their image quality. Recent advances in computer-generated holography using a camera-in-the-loop (CITL) approach have demonstrated that these issues can be overcome to improve image-fidelity by treating the system as a negative feedback control loop. Such an approach demands high bit-depth camera sensors to realise high system bandwidth. Here, we explore boosting the dynamic-range of a given imaging sensor by using a spatially varying exposure (SVE) approach. The exposure levels of adjacent pixels are spatially-multiplexed using an appropriate optical mask and the full image reconstructed from the sampled SVE image, resulting in a boosted dynamic-range with only a small sacrifice in resolution. This technique is well-tailored to CITL requirements as it promises to boost the dynamic range of the imaging sensor in a single image acquisition. We present our findings on the viability of this approach within the context of CGH displays.

Single-Image HDR Reconstruction by Multi-Exposure Generation

Abstract: High dynamic range (HDR) imaging is an indispensable technique in modern photography. Traditional methods focus on HDR reconstruction from multiple images, solving the core problems of image alignment, fusion, and tone mapping, yet having a perfect solution due to ghosting and other visual artifacts in the reconstruction. Recent attempts at single-image HDR reconstruction show a promising alternative: by learning to map pixel values to their irradiance using a neural network, one can bypass the align-and-merge pipeline completely yet still obtain a high-quality HDR image. In this work, we propose a weakly supervised learning method that inverts the physical image formation process for HDR reconstruction via learning to generate multiple exposures from a single image. Our neural network can invert the camera response to reconstruct pixel irradiance before synthesizing multiple exposures and hallucinating details in under- and over-exposed regions from a single input image. To train the network, we propose a representation loss, a reconstruction loss, and a perceptual loss applied on pairs of under- and over-exposure images and thus do not require HDR images for training. Our experiments show that our proposed model can effectively reconstruct HDR images. Our qualitative and quantitative results show that our method achieves state-of-the-art performance on the DrTMO dataset. Our code is available at https://github.com/VinAIResearch/single_image_hdr.