اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدIntroducing A Public Stereoscopic 3D High Dynamic Range (SHDR) Video Database
67
0
0.0
(
0
)
نشر من قبل
Amin Banitalebi-Dehkordi
تاريخ النشر
2018
مجال البحث
هندسة إلكترونية
والبحث باللغة
English
تأليف
Amin Banitalebi-Dehkordi
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
High Dynamic Range (HDR) displays and cameras are paving their ways through the consumer market at a rapid growth rate. Thanks to TV and camera manufacturers, HDR systems are now becoming available commercially to end users. This is taking place only a few years after the blooming of 3D video technologies. MPEG/ITU are also actively working towards the standardization of these technologies. However, preliminary research efforts in these video technologies are hammered by the lack of sufficient experimental data. In this paper, we introduce a Stereoscopic 3D HDR (SHDR) database of videos that is made publicly available to the research community. We explain the procedure taken to capture, calibrate, and post-process the videos. In addition, we provide insights on potential use-cases, challenges, and research opportunities, implied by the combination of higher dynamic range of the HDR aspect, and depth impression of the 3D aspect.
قيم البحث
اقرأ أيضاً
Visual Attention Models (VAMs) predict the location of an image or video regions that are most likely to attract human attention. Although saliency detection is well explored for 2D image and video content, there are only few attempts made to design
3D saliency prediction models. Newly proposed 3D visual attention models have to be validated over large-scale video saliency prediction datasets, which also contain results of eye-tracking information. There are several publicly available eye-tracking datasets for 2D image and video content. In the case of 3D, however, there is still a need for large-scale video saliency datasets for the research community for validating different 3D-VAMs. In this paper, we introduce a large-scale dataset containing eye-tracking data collected from 61 stereoscopic 3D videos (and also 2
Due to the large amount of data that point clouds represent and the differences in geometry of successive frames, the generation of motion vectors for an entire point cloud dataset may require a significant amount of time and computational resources.
With that in mind, we provide a 3D motion vector database for all frames of two popular dynamic point cloud datasets. The motion vectors were obtained through translational motion estimation procedure that partitions the point clouds into blocks of dimensions M x M x M , and for each block, a motion vector is estimated. Our database contains motion vectors for M = 8 and M = 16. The goal of this work is to describe this publicly available 3D motion vector database that can be used for different purposes, such as compression of dynamic point clouds.
Over the past decade, many computational saliency prediction models have been proposed for 2D images and videos. Considering that the human visual system has evolved in a natural 3D environment, it is only natural to want to design visual attention m
odels for 3D content. Existing monocular saliency models are not able to accurately predict the attentive regions when applied to 3D image/video content, as they do not incorporate depth information. This paper explores stereoscopic video saliency prediction by exploiting both low-level attributes such as brightness, color, texture, orientation, motion, and depth, as well as high-level cues such as face, person, vehicle, animal, text, and horizon. Our model starts with a rough segmentation and quantifies several intuitive observations such as the effects of visual discomfort level, depth abruptness, motion acceleration, elements of surprise, size and compactness of the salient regions, and emphasizing only a few salient objects in a scene. A new fovea-based model of spatial distance between the image regions is adopted for considering local and global feature calculations. To efficiently fuse the conspicuity maps generated by our method to one single saliency map that is highly correlated with the eye-fixation data, a random forest based algorithm is utilized. The performance of the proposed saliency model is evaluated against the results of an eye-tracking experiment, which involved 24 subjects and an in-house database of 61 captured stereoscopic videos. Our stereo video database as well as the eye-tracking data are publicly available along with this paper. Experiment results show that the proposed saliency prediction method achieves competitive performance compared to the state-of-the-art approaches.
High dynamic range (HDR) imaging from multiple low dynamic range (LDR) images has been suffering from ghosting artifacts caused by scene and objects motion. Existing methods, such as optical flow based and end-to-end deep learning based solutions, ar
e error-prone either in detail restoration or ghosting artifacts removal. Comprehensive empirical evidence shows that ghosting artifacts caused by large foreground motion are mainly low-frequency signals and the details are mainly high-frequency signals. In this work, we propose a novel frequency-guided end-to-end deep neural network (FHDRNet) to conduct HDR fusion in the frequency domain, and Discrete Wavelet Transform (DWT) is used to decompose inputs into different frequency bands. The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details. Using a U-Net as the backbone, we propose two novel modules: merging module and frequency-guided upsampling module. The merging module applies the attention mechanism to the low-frequency components to deal with the ghost caused by large foreground motion. The frequency-guided upsampling module reconstructs details from multiple frequency-specific components with rich details. In addition, a new RAW dataset is created for training and evaluating multi-frame HDR imaging algorithms in the RAW domain. Extensive experiments are conducted on public datasets and our RAW dataset, showing that the proposed FHDRNet achieves state-of-the-art performance.
The paper proposes a method to effectively fuse multi-exposure inputs and generates high-quality high dynamic range (HDR) images with unpaired datasets. Deep learning-based HDR image generation methods rely heavily on paired datasets. The ground trut
h provides information for the network getting HDR images without ghosting. Datasets without ground truth are hard to apply to train deep neural networks. Recently, Generative Adversarial Networks (GAN) have demonstrated their potentials of translating images from source domain X to target domain Y in the absence of paired examples. In this paper, we propose a GAN-based network for solving such problems while generating enjoyable HDR results, named UPHDR-GAN. The proposed method relaxes the constraint of paired dataset and learns the mapping from LDR domain to HDR domain. Although the pair data are missing, UPHDR-GAN can properly handle the ghosting artifacts caused by moving objects or misalignments with the help of modified GAN loss, improved discriminator network and useful initialization phase. The proposed method preserves the details of important regions and improves the total image perceptual quality. Qualitative and quantitative comparisons against other methods demonstrated the superiority of our method.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
