Current binocular stereoscopic displays cause visual discomfort when objects with large disparities are present in the scene. One solution for improving visual comfort is synthetic depth of field processing, a techniq...
详细信息
ISBN:
(纸本)0819450235
Current binocular stereoscopic displays cause visual discomfort when objects with large disparities are present in the scene. One solution for improving visual comfort is synthetic depth of field processing, a technique which simulates the characteristics of the human visual system. With this technique, visual comfort is improved by blurring portions of the background and/or foreground in the scene. However, this technique has the drawback of degrading overall image quality because the blurring is typically applied to both left and right images. To lessen the visual discomfort caused by large disparities while maintaining high perceived image quality, we used a novel disparity-based asymmetrical filtering technique. Asymmetrical filtering, which refers to filtering applied to the image of one eye only, has been shown to maintain the sharpness of a stereoscopic image, provided that the amount of filtering is low. Disparity-based asymmetrical filtering uses the disparity information in a stereoscopic image to control the severity of blurring. We investigated the effects of this technique on stereoscopic video by measuring visual comfort and apparent sharpness. Our results indicate that disparity-based asymmetrical filtering does not always improve visual comfort but it maintains image quality.
Quanta image sensors are a novel paradigm in image sensor technology. Their direct application to quanta image sensors-based imaging systems is challenging because a bit-plane image is a set of binary images. In this ...
详细信息
ISBN:
(纸本)9798331529543;9798331529550
Quanta image sensors are a novel paradigm in image sensor technology. Their direct application to quanta image sensors-based imaging systems is challenging because a bit-plane image is a set of binary images. In this paper, we introduce spatiotemporal priors based on the intensity invariance and smoothness characteristics of the motion vector. Specifically, we model when the image sequences align with the correct motion vector, the spatiotemporal structure becomes more consistent. Moreover, the spatial smoothness prior is incorporated through the smoothing filtering of the evaluation metrics of motion vector candidates. The experimental results show that the proposed method is more effective than conventional methods.
This paper presents a concise end-to-end visual analysis motivated super-resolution model VASR for image reconstruction. Compatible with the existing machine vision feature coding framework, the features extracted fro...
详细信息
ISBN:
(纸本)9781665475921
This paper presents a concise end-to-end visual analysis motivated super-resolution model VASR for image reconstruction. Compatible with the existing machine vision feature coding framework, the features extracted from the machine vision task model are super-resolution amplified to reconstruct the original image for human vision. The experimental results show that without additional bit-streams, VASR can well complete the task of image reconstruction based on the extracted machine features, and has achieved good results on COCO, Openimages, TVD, and DIV2K datasets.
An algorithm is presented to view interpolation of dynamic events in real-time across time and space. Two temporal and two spatial flow fields are estimated from four images captured by two cameras at two different ti...
详细信息
ISBN:
(纸本)0819450235
An algorithm is presented to view interpolation of dynamic events in real-time across time and space. Two temporal and two spatial flow fields are estimated from four images captured by two cameras at two different times. Hybrid gradient- and correlation-based motion estimation is used to compute optical flow fields with high density and accuracy. Based on the flow fields, texture coordinates of small textured squares are computed and a new image is composed at an arbitrary viewpoint and time. Real-time processing is possible through vectorized implementation of computational demanding functions and visualization using OpenGL and standard graphics hardware. The spatio-temporal view interpolation algorithm is applicable to non-rigid events, does not use explicit 3D models, and requires no user input.
This paper proposes Graph Grouping (GG) loss for metric learning and its application to face verification. GG loss predisposes image embeddings of the same identity to be close to each other, and those of different id...
详细信息
ISBN:
(纸本)9781728180687
This paper proposes Graph Grouping (GG) loss for metric learning and its application to face verification. GG loss predisposes image embeddings of the same identity to be close to each other, and those of different identities to be far from each other by constructing and optimizing graphs representing the relation between images. Further, to reduce the computational cost, we propose an efficient way to compute GG loss for cases where embeddings are L-2 normalized. In experiments, we demonstrate the effectiveness o(f) the proposed method for face verification on the VoxCeleb dataset. The results show that the proposed GG loss outperforms conventional losses for metric learning.
The digital fish provenance and quality tracking system is essential for the seafood supply chain. As a part of this system, we develop a vision-based fish processing system to automatically perform fish freshness est...
详细信息
ISBN:
(纸本)9781728180687
The digital fish provenance and quality tracking system is essential for the seafood supply chain. As a part of this system, we develop a vision-based fish processing system to automatically perform fish freshness estimation, size measurement and species classification. Under the constrained illumination environment, our system is able to auto-process the fish selection, thus greatly reduce the human labour and bring trust and efficiency to the seafood supply chain from catch to market.
In the age of digital content creation and distribution, steganography, that is, hiding of secret data within another data is needed in many applications, such as in secret communication between two parties, piracy pr...
详细信息
ISBN:
(纸本)9781728185514
In the age of digital content creation and distribution, steganography, that is, hiding of secret data within another data is needed in many applications, such as in secret communication between two parties, piracy protection, etc. In image steganography, secret data is generally embedded within the image through an additional step after a mandatory image enhancement process. In this paper, we propose the idea of embedding data during the image enhancement process. This saves the additional work required to separately encode the data inside the cover image. We used the Alpha-Trimmed mean filter for image enhancement and XOR of the 6 MSBs for embedding the two bits of the bitstream in the 2 LSBs whereas the extraction is a reverse process. Our obtained quantitative and qualitative results are better than a methodology presented in a very recent paper.
RDPlot is an open source GUI application for plotting Rate-Distortion (RD)-curves and calculating Bjontegaard Delta (BD) statistics [1]. It supports parsing the output of commonly used reference software packages, par...
详细信息
The application of the wavelet transform in imageprocessing is most frequently based on a separable construction. Lines and columns in an image are treated independently and the basis functions are simple, products o...
详细信息
ISBN:
(纸本)0819450235
The application of the wavelet transform in imageprocessing is most frequently based on a separable construction. Lines and columns in an image are treated independently and the basis functions are simple, products of the corresponding one dimensional functions. Such method keeps simplicity in design and computation, but is not capable of capturing properly all the properties of an image. In this paper, a new truly separable. discrete multi-directional transform is proposed with a subsampling method based on lattice theory. Alternatively, the subsampling can be omitted and this leads to a multi-directional frame. This transform can be applied in many areas like denoising, non-linear approximation and compression. The results on non-linear approximation and denoising show very interesting gains compared to the standard two-dimensional analysis.
Learning-based image compression has reached the performance of classical methods such as BPG. One common approach is to use an autoencoder network to map the pixel information to a latent space and then approximate t...
详细信息
ISBN:
(纸本)9781728185514
Learning-based image compression has reached the performance of classical methods such as BPG. One common approach is to use an autoencoder network to map the pixel information to a latent space and then approximate the symbol probabilities in that space with a context model. During inference, the learned context model provides symbol probabilities, which are used by the entropy encoder to obtain the bitstream. Currently, the most effective context models use autoregression, but autoregression results in a very high decoding complexity due to the serialized data processing. In this work, we propose a method to parallelize the autoregressive process used for image compression. In our experiments, we achieve a decoding speed that is over 8 times faster than the standard autoregressive context model almost without compression performance reduction.
暂无评论