.png){kind=icon}
返回
Vector Regression Functions for Texture Compression
.png){kind=icon}
PRE
AI
DOI：10.1145/2818996.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Raster images are the standard format for texture mapping, but they suffer from limited resolution. Vector graphics are resolution-independent but are less general and more difficult to implement on a GPU. We propose a hybrid representation called vector regression functions (VRFs), which compactly approximate any point-sampled image and support GPU texture mapping, including random access and filtering operations. Unlike standard GPU texture compression, VRFs provide a variable-rate encoding in which piecewise smooth regions compress to the square root of the original size. Our key idea is to represent images using the multilayer perceptron, allowing general encoding via regression and efficient decoding via a simple GPU pixel shader. We also propose a content-aware spatial partitioning scheme to reduce the complexity of the neural network model. We demonstrate benefits of our method including its quality, size, and runtime speed.
Keyword:
Algorithms
Theory
Experimentation
Texture compression
vector graphics
neural network
machine learning
real-time rendering
graphics hardware
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.5
论文数:
4.8K
被引数:
3.6W
机构
引用论文
分享收藏
Leydig Cells within the Lamina Propria of Seminiferous Tubules in Four Patients with Azoospermia.png)
Andrologia
OAAI
AndrologiaIF0
OAAI分享收藏
查看更多内容