A Maximum &lt;italic&gt;a Posteriori&lt;/italic&gt; Estimation Framework for Robust High Dynamic Range Video Synthesis

Li, Yuelong; Lee, Chul; Monga, Vishal

doi:10.1109/tip.2016.2642790

Cited by 16 publications

(23 citation statements)

References 46 publications

(126 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluate the performance of the proposed algorithm with those of two state-of-the-art HDR video synthesis algorithms: Kalantari et al's algorithm [19] and Li et al's algorithm [21], in terms of both subjective and objective aspects. The source codes for these algorithms are publicly provided by the respective authors [19], [21]. We used the optimal parameter settings to provide the best overall visual quality.…”

Section: Resultsmentioning

confidence: 99%

“…The framework adjusts the settings of the metering algorithm to choose exposures that minimize visual artifacts after recombination into an HDR sequence. Li et al [21] formulated motion estimation as an optimization problem. Specifically, they used the rank minimization technique and multi-scale regression to respectively obtain the background and foreground of the scene.…”

Section: B Hdr Video Synthesismentioning

confidence: 99%

“…Kalantari et al [19] used the PatchMatch algorithm [20] for correspondence estimation and optical flow-based registration to enhance the temporal coherency. Li et al [21] obtained the background of the HDR frame using rank-minimization, and the foreground via multi-scale adaptive kernel regression by considering motion estimation as an optimization problem.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

High Dynamic Range Video Synthesis Using Superpixel-Based Illuminance-Invariant Motion Estimation

Lee

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

We propose a robust high dynamic range (HDR) video synthesis algorithm using the superpixel-based illuminance-invariant motion estimation technique. The proposed algorithm first selects an input frame in an alternating exposed input video as the reference. Then, the correspondences between two adjacent frames are estimated by employing a feature descriptor, which is robust against illuminance variation, and a superpixel segmentation technique. Next, the input frames are warped to the reference frame using the estimated motion maps. Finally, the final HDR frame is synthesized by constructing a weight map, which can handle complex motions and poor exposures by considering the underlying structures in the input frames. Experimental results on real test sequences show that the proposed algorithm can provide high-quality HDR videos compared with those obtained by state-of-the-art algorithms in terms of both subjective and objective evaluations. INDEX TERMS High dynamic range (HDR) video synthesis, HDR imaging, motion estimation.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: B Hdr Video Synthesismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

High Dynamic Range Video Synthesis Using Superpixel-Based Illuminance-Invariant Motion Estimation

Lee

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Perhaps, the main reason is that this problem is more challenging than that of producing HDR images; in addition to producing artifact‐free HDR images, a high‐quality HDR video requires the frames to be temporally coherent. Although a few methods have been proposed to address this problem [KUWS03, MG11, KSB∗13, LLM17], they are typically slow and not able to handle challenging cases (see Figs. 11, 13, and 14).…”

Section: Introductionmentioning

confidence: 99%

Deep HDR Video from Sequences with Alternating Exposures

Kalantari¹,

Ramamoorthi

2019

Computer Graphics Forum

View full text Add to dashboard Cite

A practical way to generate a high dynamic range (HDR) video using off‐the‐shelf cameras is to capture a sequence with alternating exposures and reconstruct the missing content at each frame. Unfortunately, existing approaches are typically slow and are not able to handle challenging cases. In this paper, we propose a learning‐based approach to address this difficult problem. To do this, we use two sequential convolutional neural networks (CNN) to model the entire HDR video reconstruction process. In the first step, we align the neighboring frames to the current frame by estimating the flows between them using a network, which is specifically designed for this application. We then combine the aligned and current images using another CNN to produce the final HDR frame. We perform an end‐to‐end training by minimizing the error between the reconstructed and ground truth HDR images on a set of training scenes. We produce our training data synthetically from existing HDR video datasets and simulate the imperfections of standard digital cameras using a simple approach. Experimental results demonstrate that our approach produces high‐quality HDR videos and is an order of magnitude faster than the state‐of‐the‐art techniques for sequences with two and three alternating exposures.

show abstract

“…High dynamic range (HDR) contents have recently received significant recognition in many multimedia applications, such as digital photography, ultra-high-definition movies and television, video games, medical imaging, and so on [1][2][3]. Unlike traditional low dynamic range (LDR) images, HDR images provide a large range of luminance, and they could more accurately represent real scenes and provide rich color details and light levels as they are perceived by human eye [4].…”

Section: Introductionmentioning

confidence: 99%

Novel Robust High Dynamic Range Image Watermarking Algorithm Against Tone Mapping

Bai¹,

Jiang²,

Jiang³

et al. 2018

KSII TIIS

View full text Add to dashboard Cite

High dynamic range (HDR) images are becoming pervasive due to capturing or rendering of a wider range of luminance, but their special display equipment is difficult to be popularized because of high cost and technological problem. Thus, HDR images must be adapted to the conventional display devices by applying tone mapping (TM) operation, which puts forward higher requirements for intellectual property protection of HDR images. As the robustness presents regional diversity in the low dynamic range (LDR) watermarked image after TM, which is different from the traditional watermarking technologies, a concept of watermarking activity is defined and used to distinguish the essential distinction of watermarking between LDR image and HDR image in this paper. Then, a novel robust HDR image watermarking algorithm is proposed against TM operations. Firstly, based on the hybrid processing of redundant discrete wavelet transform and singular value decomposition, the watermark is embedded by modifying the structure information of the HDR image. Distinguished from LDR image watermarking, the high embedding strength can cause more obvious distortion in the high brightness regions of HDR image than the low brightness regions. Thus, a perceptual brightness mask with low complexity is designed to improve the imperceptibility further. Experimental results show that the proposed algorithm is robust to the existing TM operations, with taking into account the imperceptibility and embedded capacity, which is superior to the current state-of-art HDR image watermarking algorithms.

show abstract

A Maximum <italic>a Posteriori</italic> Estimation Framework for Robust High Dynamic Range Video Synthesis

Cited by 16 publications

References 46 publications

High Dynamic Range Video Synthesis Using Superpixel-Based Illuminance-Invariant Motion Estimation

High Dynamic Range Video Synthesis Using Superpixel-Based Illuminance-Invariant Motion Estimation

Deep HDR Video from Sequences with Alternating Exposures

Novel Robust High Dynamic Range Image Watermarking Algorithm Against Tone Mapping

Contact Info

Product

Resources

About