We have witnessed the revolutionary progress of learned image compression despite a short history of this field. Some challenges still remain such as computational complexity that prevent the practical application of ...
详细信息
We have witnessed the revolutionary progress of learned image compression despite a short history of this field. Some challenges still remain such as computational complexity that prevent the practical application of learning-based codecs. In this paper, we address the issue of heavy time complexity from the view of arithmetic coding. Prevalent learning-based image compression scheme first maps the natural image into latent representations and then conduct arithmetic coding on quantized latent maps. Previous arithmetic coding schemes define the start and end value of the arithmetic codebook as the minimum and maximum of the whole latent maps, ignoring the fact that the value ranges in most channels are shorter. Hence, we propose to use a channel-adaptive codebook to accelerate arithmetic coding. We find that the latent channels have different frequency-related characteristics, which are verified by experiments of neural frequency filtering. Further, the value ranges of latent maps are different across channels which are relatively image-independent. The channel-adaptive characteristics allow us to establish efficient prior codebooks that cover more appropriate ranges to reduce the runtime. Experimental results demonstrate that both the arithmetic encoding and decoding can be accelerated while preserving the rate-distortion performance of compression model.
Multi-Aspect SAR can obtain rich backscatter information about the illuminated scene. For different kinds of targets in the scene, scattering information related to the geometric characteristics of the target is shown...
详细信息
The circular synthetic aperture radar (SAR) can observe the experimental scene from all angles. The backscatter intensity of the target in the scene can be obtained. Different targets in the imaging scene show differe...
详细信息
Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distort...
详细信息
Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task. To alleviate this problem, we raise t...
详细信息
Single image super-resolution (SISR) aims to recover the high-resolution (HR) image from its low-resolution (LR) input image. With the development of deep learning, SISR has achieved great progress. However, It is sti...
详细信息
This paper assesses the capability of Compact Polarized (CP) Synthetic Aperture Radar (SAR) to explore ocean surface backscattering by reconstructing the pseudo quad-pol data. Besides using Souyris’s or Nord’s algor...
详细信息
SAR image understanding is a significant but also challenging issue in practice. In order to detect the difference between single-polarized and polarimetric SAR (PolSAR) data and explore more information from the pre ...
详细信息
Video coding is a mathematical optimization problem of rate and distortion essentially. To solve this complex optimization problem in practice, two popular video coding frameworks have been developed: block-based hybr...
详细信息
Video coding is a mathematical optimization problem of rate and distortion essentially. To solve this complex optimization problem in practice, two popular video coding frameworks have been developed: block-based hybrid video coding and end-to-end learned video coding. If we rethink video coding from the perspective of optimization, we find that the existing two frameworks represent two directions of optimization solutions. Block-based hybrid video coding represents the discrete optimization solution because those irrelevant coding modes are discrete in mathematics. The discrete solution provides multiple starting points (i.e. modes) in global optimization space and then searches for the best one among them. However, the search-based optimization algorithm is not efficient enough. On the other hand, end-to-end learned video coding represents the continuous optimization solution because the optimization algorithm of deep learning, gradient descent, is based on a continuous function. The continuous solution optimizes a group of model parameters efficiently by such a numerical algorithm. However, limited by only one starting point, it is easy to fall into the local optimum. To better solve the optimization problem, we propose a hybrid of discrete and continuous optimization video coding. We regard video coding as a hybrid of the discrete and continuous optimization problem, and use both search and numerical algorithm to solve it. Our idea is to provide multiple discrete starting points in the global space and optimize the local optimum around each point by numerical algorithm efficiently. Finally, we search for the global optimum among those local optimums. Guided by the hybrid optimization idea, we design a hybrid optimization video coding framework, which is built on continuous deep networks entirely and also contains some discrete modes. We conduct a comprehensive set of experiments to verify the efficiency of our hybrid optimization. Compared to the continuous opti
Microwave photonic (MWP) SAR technology can realize large bandwidth even across multiple wavebands and therefore improves the imaging resolution significantly. However, when targets are illuminated by the electromagne...
Microwave photonic (MWP) SAR technology can realize large bandwidth even across multiple wavebands and therefore improves the imaging resolution significantly. However, when targets are illuminated by the electromagnetic wave with such an across-band bandwidth, their scattering characteristics will change with signal frequency, which is not taken into consideration for conventional SAR imaging. In this paper, in order to investigate the resolution and optimize the imaging of MWP SAR, we first design several typical structures and conduct electromagnetic simulations on them, from which, we obtain the variation of scattering characteristics within an across-band bandwidth. Then, we use different focusing approaches for one-dimensional imaging processing and adopt different evaluation indicators to evaluate the performance of these methods comprehensively. Finally, with detailed analysis, we give suggestions on the selection of compression methods for different structures at different SNRs.
暂无评论