Texture Image Compression Algorithm Based on Self-Organizing Neural Network

Abstract

With the rapid development of science and technology, human beings have gradually stepped into a brand-new digital era. Virtual reality technology has brought people an immersive experience. In order to enable users to get a better virtual reality experience, the pictures produced by virtual skillfully must be realistic enough and support users' real-time interaction. So interactive real-time photorealistic rendering becomes the focus of research. Texture mapping is a technology proposed to solve the contradiction between real time and reality. It has been widely studied and used since it was proposed. However, due to limited bandwidth and memory storage, it brings challenges to the stain dyeing of many large texture images, so texture compression is introduced. Texture compression can improve the utilization rate of cache but also greatly reduce the pressure on data transmission caused by the system, which largely solves the problem of real-time rendering of realistic graphics. Due to the particularity of texture image compression, it is necessary to consider not only the quality of texture image after compression ratio and decompression but also whether the algorithm is compatible with mainstream graphics cards. On this basis, we put forward the texture image compression method based on self-organizing mapping, the experiment results show that our method has achieved good results, and it is superior to other methods in most performance indexes.

Research on Multichannel 3D Oil Painting Style Rendering Model Based on 3DS Max

“…Not only texture compression may increase cache use rates but it can also significantly lessen the strain on data transfer created by the system, which in turn cause to address the issue of real-time rendering of realistic visuals to a substantial extent. Given the uniqueness of texture image compression, it is vital to evaluate not only the quality of the texture image after compression ratio and decompression, but also if the technique is compatible with unpopular graphics cards as well as the compression ratio [22]. In P 2 GAN (existing) method nonconvergence occurs when the model parameters fluctuate, destabilize, and never reach a state of convergence.…”

“…In Chip GAN (existing), realistic western paintings have been created using style transfer techniques applied to photographs. p2-GAN [23] ChipGAN [24] CycleGAN [25] Self-organizing neural network [22] p2-GAN [23] ChipGAN [24] CycleGAN [25] Self-organizing neural network [22] Figure 8: Comparison of rate of information loss of existing and proposed techniques. However, since the painting techniques used in Chinese and western paintings are fundamentally different, simply using current methods to the transfer of Chinese ink-wash painting style would not provide adequate results [24].…”

“…In application, the dataset used to corroborate the findings of p2-GAN [23] Self-organizing neural network [22] ChipGAN [24] CycleGAN [25] p2-GAN [23] ChipGAN [24] CycleGAN [25] Self-organizing neural network [22]…”

A Novel Image Compression Algorithm Based on Autoencoder for Biometric Template Protection Scheme

“…Inter-pixel aggregation is the term for this kind of aggregation. Spatial aggregation is another name for this type of aggregation (4) .…”

Empirical Compression Features of Mobile Computing and Data Applications Using Deep Neural Networks

“…But the hierarchical model does not provide a structural view with any analytical framework; thus, a separate algorithm is integrated. Even in recent times, the researchers have directed the research model using a deep neural network where the design is completely based on complementary mobile terminals [13][14][15][16][17]. If each terminal in the mobile nodes is stationary, then insignifcant data flters will be removed from the system.…”