Showing papers on "High dynamic range published in 2022"

Event-Based Vision: A Survey

Abstract: Event cameras are bio-inspired sensors that differ from conventional frame cameras: Instead of capturing images at a fixed rate, they asynchronously measure per-pixel brightness changes, and output a stream of events that encode the time, location and sign of the brightness changes. Event cameras offer attractive properties compared to traditional cameras: high temporal resolution (in the order of μs), very high dynamic range (140 dB versus 60 dB), low power consumption, and high pixel bandwidth (on the order of kHz) resulting in reduced motion blur. Hence, event cameras have a large potential for robotics and computer vision in challenging scenarios for traditional cameras, such as low-latency, high speed, and high dynamic range. However, novel methods are required to process the unconventional output of these sensors in order to unlock their potential. This paper provides a comprehensive overview of the emerging field of event-based vision, with a focus on the applications and the algorithms developed to unlock the outstanding properties of event cameras. We present event cameras from their working principle, the actual sensors that are available and the tasks that they have been used for, from low-level vision (feature detection and tracking, optic flow, etc.) to high-level vision (reconstruction, segmentation, recognition). We also discuss the techniques developed to process events, including learning-based techniques, as well as specialized processors for these novel sensors, such as spiking neural networks. Additionally, we highlight the challenges that remain to be tackled and the opportunities that lie ahead in the search for a more efficient, bio-inspired way for machines to perceive and interact with the world.

NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results

Abstract: This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022. This manuscript focuses on the competition set-up, datasets, the proposed methods and their results. The challenge aims at estimating an HDR image from multiple respective low dynamic range (LDR) observations, which might suffer from under-or over-exposed regions and different sources of noise. The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i.e. solutions can not exceed a given number of operations). In Track 2, participants are asked to minimize the complexity of their solutions while imposing a constraint on fidelity scores (i.e. solutions are required to obtain a higher fidelity score than the prescribed baseline). Both tracks use the same data and metrics: Fidelity is measured by means of PSNR with respect to a ground-truth HDR image (computed both directly and with a canonical tonemapping operation), while complexity metrics include the number of Multiply-Accumulate (MAC) operations and runtime (in seconds).

NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images

Abstract: Neural Radiance Fields (NeRF) is a technique for high quality novel view synthesis from a collection of posed input images. Like most view synthesis methods, NeRF uses tonemapped low dynamic range (LDR) as input; these images have been processed by a lossy camera pipeline that smooths detail, clips highlights, and distorts the simple noise distribution of raw sensor data. We modify NeRF to instead train directly on linear raw images, preserving the scene's full dynamic range. By rendering raw output images from the resulting NeRF, we can perform novel high dynamic range (HDR) view synthesis tasks. In addition to changing the camera viewpoint, we can manipulate focus, exposure, and tonemapping after the fact. Although a single raw image appears significantly more noisy than a postprocessed one, we show that NeRF is highly robust to the zeromean distribution of raw noise. When optimized over many noisy raw inputs (25–200), NeRF produces a scene representation so accurate that its rendered novel views outperform dedicated single and multi-image deep raw denoisers run on the same wide baseline input images. As a result, our method, which we call RawNeRF, can reconstruct scenes from extremely noisy images captured in near-darkness.

HDR CMOS Image Sensors for Automotive Applications

Abstract: Because of various purposes and high dynamic range (HDR) of brightness of objects in automotive applications, HDR image capture is a primary requirement. In this article, HDR CMOS image sensor (CIS) technology and its automotive applications are discussed including application requirements, basic HDR approaches and trends of HDR CMOS image sensor technologies, advantages and disadvantages for automotive application, and future prospect of the HDR technology. LED flicker caused by time aliasing effect and motion artifacts are two major issues in conventional multiple exposure HDR (MEHDR) approach, and several HDR technologies have been introduced for automotive applications. The advancements of image sensor fabrication technology, for instance, backside illumination (BSI) process and pixel level hybrid wafer bonding, have created new trends in the HDR technology.

High dynamic range and super-resolution from raw image bursts

Abstract: Photographs captured by smartphones and mid-range cameras have limited spatial resolution and dynamic range, with noisy response in underexposed regions and color artefacts in saturated areas. This paper introduces the first approach (to the best of our knowledge) to the reconstruction of highresolution, high-dynamic range color images from raw photographic bursts captured by a handheld camera with exposure bracketing. This method uses a physically-accurate model of image formation to combine an iterative optimization algorithm for solving the corresponding inverse problem with a learned image representation for robust alignment and a learned natural image prior. The proposed algorithm is fast, with low memory requirements compared to state-of-the-art learning-based approaches to image restoration, and features that are learned end to end from synthetic yet realistic data. Extensive experiments demonstrate its excellent performance with super-resolution factors of up to ×4 on real photographs taken in the wild with hand-held cameras, and high robustness to low-light conditions, noise, camera shake, and moderate object motion.

Ultrahigh dynamic range and low noise figure programmable integrated microwave photonic filter

Abstract: Microwave photonics (MWP) has adopted a number of important concepts and technologies over the recent pasts, including photonic integration, versatile programmability, and techniques for enhancing key radio frequency performance metrics such as the noise figure and the dynamic range. However, to date, these aspects have not been achieved simultaneously in a single circuit. Here, we demonstrate, for the first time, a multi-functional integrated microwave photonic circuit that enables on-chip programmable filtering functions while achieving record-high key radio frequency metrics of >120 dB.Hz dynamic range and 15 dB of noise figure that are previously unreachable. We unlock this unique feature by versatile complex spectrum tailoring using an all integrated modulation transformer and a double injection ring resonator as a multi-function optical filtering component. This work breaks the conventional and fragmented approach of integration, functionality and performance that currently prevents the adoption of integrated MWP systems in real applications.

Lighting measurement with a 360° panoramic camera: Part 1 – Technical procedure and validation

Abstract: This study developed a 360° field of view (FOV) lighting measurement method with the aid of the Ricoh Theta Z1 panoramic camera. As versatile lighting information from all viewing directions within 360° FOV can be retrieved from a single 360° high dynamic range (HDR) image, this new method improves the lighting measurement efficiency. Part 1 of this study reported in the present paper focuses on technical procedure and validation. Firstly, all technical issues were solved for using the Theta Z1 camera to conduct 360° FOV lighting measurement with a provided and validated step-by-step procedure. A new illuminance measurement method was then developed with the aid of the Theta Z1 camera for calculating all directional illuminance data at the camera measurement point from any viewing direction within the 360° panoramic FOV, retrieved from a single 360° HDR image taken in the field. This 360° FOV lighting measurement method has average error rate of 4.0% ± 2.4% for luminance measurement and 3.1% ± 2.6% for illuminance measurement in building interiors. Reported outcomes include the detailed procedure and algorithms for the configuration, calibrations and post-image processing, and corresponding MATLAB code and Python programs are shared online.

First AI for Deep Super-resolution Wide-field Imaging in Radio Astronomy: Unveiling Structure in ESO 137-006

Abstract: We introduce the first AI-based framework for deep, super-resolution, wide-field radio interferometric imaging and demonstrate it on observations of the ESO 137-006 radio galaxy. The algorithmic framework to solve the inverse problem for image reconstruction builds on a recent “plug-and-play” scheme whereby a denoising operator is injected as an image regularizer in an optimization algorithm, which alternates until convergence between denoising steps and gradient-descent data fidelity steps. We investigate handcrafted and learned variants of high-resolution, high dynamic range denoisers. We propose a parallel algorithm implementation relying on automated decompositions of the image into facets and the measurement operator into sparse low-dimensional blocks, enabling scalability to large data and image dimensions. We validate our framework for image formation at a wide field of view containing ESO 137-006 from 19 GB of MeerKAT data at 1053 and 1399 MHz. The recovered maps exhibit significantly more resolution and dynamic range than CLEAN, revealing collimated synchrotron threads close to the galactic core.

HDR-NeRF: High Dynamic Range Neural Radiance Fields

Abstract: We present High Dynamic Range Neural Radiance Fields (HDR-NeRF) to recover an HDR radiance field from a set of low dynamic range (LDR) views with different exposures. Using the HDR-NeRF, we are able to generate both novel HDR views and novel LDR views under different exposures. The key to our method is to model the simplified physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper. The radiance field encodes the scene radiance (values vary from 0 to $+\infty$ ), which outputs the density and radiance of a ray by giving corresponding ray origin and ray direction. The tone mapper models the mapping process that a ray hitting on the camera sensor becomes a pixel value. The color of the ray is predicted by feeding the radiance and the corresponding exposure time into the tone mapper. We use the classic volume rendering technique to project the output radiance, colors and densities into HDR and LDR images, while only the input LDR images are used as the supervision. We collect a new forward-facing HDR dataset to evaluate the proposed method. Experimental results on synthetic and real-world scenes validate that our method can not only accurately control the exposures of synthesized views but also render views with a high dynamic range.

E2SRI: Learning to Super-Resolve Intensity Images from Events

Abstract: An event camera reports per-pixel intensity differences as an asynchronous stream of events with low latency, high dynamic range (HDR), and low power consumption. This stream of sparse/dense events limits the direct use of well-known computer vision applications for event cameras. Further applications of event streams to vision tasks that are sensitive to image quality issues, such as spatial resolution and blur, e.g., object detection, would benefit from a higher resolution of image reconstruction. Moreover, despite the recent advances in spatial resolution in event camera hardware, the majority of commercially available event cameras still have relatively low spatial resolutions when compared to conventional cameras. We propose an end-to-end recurrent network to reconstruct high-resolution, HDR, and temporally consistent grayscale or color frames directly from the event stream, and extend it to generate temporally consistent videos. We evaluate our algorithm on real-world and simulated sequences and verify that it reconstructs fine details of the scene, outperforming previous methods in quantitative quality measures. We further investigate how to (1) incorporate active pixel sensor frames (produced by an event camera) and events together in a complementary setting and (2) reconstruct images iteratively to create an even higher quality and resolution in the images.

Deep Learning for HDR Imaging: State-of-the-Art and Future Trends

Abstract: High dynamic range (HDR) imaging is a technique that allows an extensive dynamic range of exposures, which is important in image processing, computer graphics, and computer vision. In recent years, there has been a significant advancement in HDR imaging using deep learning (DL). This study conducts a comprehensive and insightful survey and analysis of recent developments in deep HDR imaging methodologies. We hierarchically and structurally group existing deep HDR imaging methods into five categories based on (1) number/domain of input exposures, (2) number of learning tasks, (3) novel sensor data, (4) novel learning strategies, and (5) applications. Importantly, we provide a constructive discussion on each category regarding its potential and challenges. Moreover, we review some crucial aspects of deep HDR imaging, such as datasets and evaluation metrics. Finally, we highlight some open problems and point out future research directions.

A 0.37W 143dB-Dynamic-Range 1Mpixel Backside-Illuminated Charge-Focusing SPAD Image Sensor with Pixel-Wise Exposure Control and Adaptive Clocked Recharging

Abstract: Demands for single-photon-sensitive high-dynamic-range (HDR) imaging in security, automotive, and medical applications have driven development of scalable single-photon avalanche diode (SPAD)-based image sensors. In recent years, 3D-stacking technology combined with advanced CMOS processes has enabled pixel-parallel photon counting in sub-10µm SPAD pixels. A major technical challenge in realizing high-definition SPAD image sensors lies in a trade-off between power consumption and dynamic range (DR). SPAD pixels inherently consume a considerable amount of power due to the high-voltage operation and high current gain. Power consumption from the SPAD array (P SPAD ) grows significantly with increasing incident photon flux, and often dominates over that from the readout circuit under high light conditions. Restricting maximum photon counts per frame could suppress the maximum P SPAD , at the expense of DR. To address this issue, a recharging circuit architecture must be carefully considered. Passive recharging has been widely employed for HDR imaging SPADs [1]–[3], but it is not a viable option for megapixel implementation due to the huge P SPAD , typically reaching tens of watts at excess illuminance. A clocked recharging architecture provides a scalable solution thanks to its compact circuitry and greatly reduced P SPAD at excess illuminance [4]–[6], but to date no existing SPAD sensor has simultaneously achieved megapixel resolution, sub-watt total power consumption, and > 120dB DR.

A Real-Time Semi-Supervised Deep Tone Mapping Network

Abstract: Tone mapping operators (TMOs) can compress the range of high dynamic range (HDR) images so that they can be displayed normally on the low dynamic range (LDR) devices. Recent TMOs based on deep neural networks can produce impressive results, but there are still some shortcomings. On the one hand, their supervised learning procedure requires a high-quality paired dataset which is hard to be accessed. On the other hand, they are too slow and heavy to meet the needs of practical applications. This paper proposes a real-time deep semi-supervised learning TMO to solve the above problems. The proposed method learns in a semi-supervised manner by combining the adversarial loss, cycle consistency loss, and the pixel-wise loss. The first two can simulate the image distributions in the real world from the unpaired LDR data and the latter can learn the guidance of paired LDR labels. In this way, the proposed method only requires HDR sources, unpaired high-quality LDR images, and a few well tone-mapped HDR-LDR pairs as training data. Furthermore, the proposed method divides tone mapping into luminance mapping and saturation adjustment and then processes them simultaneously. By this strategy, we can reconstruct each component more precisely. Based on the aforementioned improvements, we propose a lightweight tone mapping network that is efficient in tone mapping task (up to 5000x parameters-saving and 27x time-saving compared to the learning-based TMOs). Both quantitative and qualitative results demonstrate that the proposed method performs favorable against state-of-the-art TMOs.

Pas-Mef: Multi-Exposure Image Fusion Based On Principal Component Analysis, Adaptive Well-Exposedness And Saliency Map

Abstract: High dynamic range (HDR) imaging enables to immortalize natural scenes similar to the way that they are perceived by human observers. With regular low dynamic range (LDR) capture/display devices, significant details may not be preserved in images due to the huge dynamic range of natural scenes. To minimize the information loss and produce high quality HDR-like images for LDR screens, this study proposes an efficient multi-exposure fusion (MEF) approach with a simple yet effective weight extraction method relying on principal component analysis, adaptive well-exposedness and saliency maps. These weight maps are later refined through a guided filter and the fusion is carried out by employing a pyramidal decomposition. Experimental comparisons with existing techniques demonstrate that the proposed method produces very strong statistical and visual results.

RV-TMO: Large-Scale Dataset for Subjective Quality Assessment of Tone Mapped Images

Abstract: Tone mapping operators (TMO) are functions that map high dynamic range (HDR) images to a standard dynamic range (SDR), while aiming to preserve the perceptual cues of a scene that govern its visual quality. Despite the increasing number of studies on quality assessment of tone mapped images, current subjective quality datasets have relatively small numbers of images and subjective opinions. Moreover, existing challenges in transferring laboratory experiments to crowdsourcing platforms put a barrier for collecting large-scale datasets through crowdsourcing. In this work, we address these challenges and propose the RealVision-TMO (RV-TMO), a large-scale tone mapped image quality dataset. RV-TMO contains 250 unique HDR images, their tone mapped versions obtained using four TMOs and pairwise comparison results from seventy unique observers for each pair. To the best of our knowledge, this is the largest dataset available in the literature for quality evaluation of TMOs by the number of tone mapped images and number of annotations. Furthermore, we provide a content selection strategy to identify interesting and challenging HDR images. We also propose a novel methodology for observer screening in pairwise experiments. Our work does not only provide annotated data to benchmark existing objective quality metrics, but also paves the path to building new metrics for tone mapping quality evaluation.

High Dynamic Range Imaging for Dynamic Scenes With Large-Scale Motions and Severe Saturation

Abstract: Two key challenges exist in high dynamic range (HDR) imaging from multiexposure low dynamic range (LDR) images for dynamic scenes: 1) aligning the input images with large-scale foreground motions and 2) recovering large saturated regions from a limited number of input LDR images. To tackle these challenges, several deep convolutional neural networks have been proposed that have made significant progress. However, these methods tend to suffer from ghosting and saturation artifacts when applied to some challenging scenes. In this article, we propose an end-to-end deformable HDR imaging network, called DHDRNet, which attempts to alleviate these problems by building an effective aligning module and adopting self-guided attention. First, we analyze the alignment process in the HDR imaging task and correspondingly design a pyramidal deformable module (PDM) that aligns LDR images at multiple scales and reconstructs aligned features in a coarse-to-fine manner. In this way, the proposed DHDRNet can handle large-scale complex motions and suppress ghosting artifacts caused by misalignments. Moreover, we adopt self-guided attention to reduce the influence of saturated regions during the aligning and merging processes, which helps suppress artifacts and retain fine details in the final HDR image. Extensive qualitative and quantitative comparisons demonstrate that the proposed model outperforms the existing start-of-the-art methods and that it is robust to challenging scenes with large-scale motions and severe saturation. The source code is available at: https://github.com/Tx000/DHDRNet.

DBA-Filter: A Dynamic Background Activity Noise Filtering Algorithm for Event Cameras

Abstract: Newly emerged dynamic vision sensors (DVS) offer a great potential over traditional sensors (e.g. CMOS) since they have a high temporal resolution in the order of \(\mu s\), ultra-low power consumption and high dynamic range up to 140 dB compared to 60 dB in frame cameras. Unlike traditional cameras, the output of DVS cameras is a stream of events that encodes the location of the pixel, time, and polarity of the brightness change. An event is triggered when the change of brightness, i.e. log intensity, of a pixel exceeds a certain threshold. The output of event cameras often contains a significant amount of noise (outlier events) alongside the signal (inlier events). The main cause of that is transistor switch leakage and noise. This paper presents a dynamic background activity filtering, called DBA-filter, for event cameras based on an adaptation of the K-nearest neighbor (KNN) algorithm and the optical flow. Results show that the proposed algorithm is able to achieve a high signal to noise ratio up to 13.64 dB.

Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration

Abstract: High Dynamic Range (HDR) imaging via multi-exposure fusion is an important task for most modern imaging platforms. In spite of recent developments in both hardware and algorithm innovations, challenges remain over content association ambiguities caused by saturation, motion, and various artifacts introduced during multi-exposure fusion such as ghosting, noise, and blur. In this work, we propose an Attention-guided Progressive Neural Texture Fusion (APNT-Fusion) HDR restoration model which aims to address these issues within one framework. An efficient two-stream structure is proposed which separately focuses on texture feature transfer over saturated regions and multi-exposure tonal and texture feature fusion. A neural feature transfer mechanism is proposed which establishes spatial correspondence between different exposures based on multi-scale VGG features in the masked saturated HDR domain for discriminative contextual clues over the ambiguous image areas. A progressive texture blending module is designed to blend the encoded two-stream features in a multi-scale and progressive manner. In addition, we introduce several novel attention mechanisms, i.e., the motion attention module detects and suppresses the content discrepancies among the reference images; the saturation attention module facilitates differentiating the misalignment caused by saturation from those caused by motion; and the scale attention module ensures texture blending consistency between different coder/decoder scales. We carry out comprehensive qualitative and quantitative evaluations and ablation studies, which validate that these novel modules work coherently under the same framework and outperform state-of-the-art methods.

Characterization of 128 × 128 MM-PAD-2.1 ASIC: a fast framing hard x-ray detector with high dynamic range

Abstract: Abstract We characterize a new x-ray Mixed-Mode Pixel Array Detector (MM-PAD-2.1) Application Specific Integrated Circuit (ASIC). Using an integrating pixel front-end with dynamic charge removal architecture, the MM-PAD-2.1 ASIC extends the maximum measurable x-ray signal (in 20 keV photon units) to > 10 7 x-rays/pixel/frame while maintaining a low read noise across the full dynamic range, all while imaging continuously at a frame rate of up to 10 kHz. The in-pixel dynamic charge removal mechanism prevents saturation of the input amplifier and proceeds in parallel with signal integration to achieve deadtime-less measurements with incident x-ray rates of > 10 10 x-rays/pixel/s. The ASIC format consists of 128 × 128 square pixels each 150 μm on a side and is designed to be 3-side buttable so large arrays can be effectively tiled. Here we use both laboratory x-ray sources and the Cornell High Energy Synchrotron Source (CHESS) to characterize two single ASIC prototype detectors for both low (single x-ray) and high incident flux detection. In the first detector the ASIC was solder bump-bonded to a 500 μm thick Si sensor for efficient detection of x-rays below 20 keV, whereas the second detector used a 750 μm thick CdTe sensor for x-rays above ∼ 20 keV.

Unlimited Sampling with Local Averages

Abstract: Signal saturation or clipping is a fundamental bottleneck that limits the capability of analog-to-digital converters (ADCs). The problem arises when the input signal dynamic range is larger than ADC’s dynamic range. To overcome this issue, an alternative acquisition protocol called the Unlimited Sensing Framework (USF) was recently proposed. This non-linear sensing scheme incorporates signal folding (via modulo non-linearity) before sampling. Reconstruction then entails "unfolding" of the high dynamic range input. Taking an end-to-end approach to the USF, a hardware validation called US-ADC was recently presented. US-ADC experiments show that, in some scenarios, the samples can be more accurately modelled as local averages than ideal, pointwise measurements. In particular, this happens when the input signal frequency is much larger than the operational bandwidth of the US-ADC. Pushing such hardware limits using computational approaches motivates the study of modulo sampling and reconstruction via local averages. By incorporating a modulo-hysteresis model, both in theory and in hardware, we present a guaranteed recovery algorithm for input reconstruction. We also explore a practical method suited for low sampling rates. Our approach is validated via simulations and experiments on hardware, thus enabling a step closer to practice.

Digital image forgery detection under complex lighting using Phong reflection model

Abstract: Image manipulation is transformed into a big issue for data integrity. The use of advanced imaging technology expends the regularity of multimedia forgeries. To detect such forgeries, some effective forgery identification methods are proposed to estimate the 3D lighting fingerprints by making certain suppositions related to the surface and reflection model. Incident lighting dispersal in a scene provides a physics-based key for exposing image exploitations. The proposed technique is more relaxed for multiple light source-based forgery detection. Also, the novelty of the technique is that it considers heterogeneous image surfaces, nearby surface geometry, and texture information to assess the lighting environment. The Phong reflection model is implemented to estimate the structural profiles. The method works in two phases. In the first phase, pre-processing over selected patches is performed followed by angle and error estimations in the second phase. To identify such forgeries, elevation angles ϑ concerning mounted light sources are estimated. The value of the elevation angle is computed for various patches of the image. The proposed method is relevant for a wide range of objects present in the image, i.e., not only limited to head positions, etc. To build up and validate the technique, comprehensive testing on the synthetic image dataset is done. Synthetic images are designed under different intensity light sources. Experimental results demonstrate a better forgery detection accuracy compared with other state-of-the-art methods in this domain. Also, the proposed technique is tested for generalized forged images. A comparative analysis with other related techniques is done to validate the proposed method using a synthetic image dataset. The results are pertinent to all type of images, and an error threshold is limited to 8 degrees with respect to the illuminant position.

Realistic Luminance in VR

Abstract: As virtual reality (VR) headsets continue to achieve ever more immersive visuals along the axes of resolution, field of view, focal cues, distortion mitigation, and so on, the luminance and dynamic range of these devices falls far short of widely available consumer televisions. While work remains to be done on the display architecture side, power and weight limitations in head-mounted displays pose a challenge for designs aiming for high luminance. In this paper, we seek to gain a basic understanding of VR user preferences for display luminance values in relation to known, real-world luminances for immersive, natural scenes. To do so, we analyze the luminance characteristics of an existing high-dynamic-range (HDR) panoramic image dataset, build an HDR VR headset capable of reproducing over 20,000 nits peak luminance, and conduct a first-of-its-kind study on user brightness preferences in VR. We conclude that current commercial VR headsets do not meet user preferences for display luminance, even for indoor scenes.

Real-Time Tone Mapping: A Survey and Cross-Implementation Hardware Benchmark

Abstract: The rising demand for high quality display has ensued active research in high dynamic range (HDR) imaging, which has the potential to replace the standard dynamic range imaging. This is due to HDR's features like accurate reproducibility of a scene with its entire spectrum of visible lighting and color depth. But this capability comes with expensive capture, display, storage and distribution resource requirements. Also, display of HDR images/video content on an ordinary display device with limited dynamic range requires some form of adaptation. Many adaptation algorithms, widely known as tone mapping operators, have been studied and proposed in the last few decades. In this state of the art report, we present a comprehensive survey of 50+ tone mapping algorithms that have been implemented on hardware for acceleration and real-time performance. These algorithms have been adapted or redesigned to make them hardware-friendly. All real-time application poses strict timing constraints which requires time exact processing of the algorithm. This design challenge require novel solution, and in this report we focus on these issues. In this we survey will discuss those tonemap algorithms which have been implemented on GPU [1-10], FPGA [11-41], and ASIC [42-53] in terms of their hardware specifications and performance. Output image quality is an important metric for tonemap algorithms. From our literature survey we found that, various objective quality metrics have been used to demonstrate the functionality of adapting the algorithm on hardware platform. We have compiled and studied all the metrics used in this survey [54-67]. Finally, in this report we demonstrate the link between hardware cost and image quality thereby illustrating the underlying trade-off which will be useful for the research community.

Bidirectional Motion Estimation with Cyclic Cost Volume for High Dynamic Range Imaging

Abstract: We propose a high dynamic range (HDR) imaging algorithm based on bidirectional motion estimation. First, we develop a motion estimation network with the cyclic cost volume and spatial attention maps to estimate accurate optical flows between input low dynamic range (LDR) images. Then, we develop the dynamic local fusion network that combines the warped and reference inputs to generate a synthesized image by exploiting local information. Finally, to further improve the synthesis performance, we develop the global refinement network that generates a residual image by exploiting global information. Experimental results on the dataset from the NTIRE 2022 HDR Challenge Track 1 (Low-complexity constrain) demonstrate the effectiveness of the proposed HDR image synthesis algorithm.