返回
Optimized wavelet-based texture representation and streaming for GPU texture mapping
DOI:10.1007/s11042-017-4433-3.png)
摘要
En 中文
Because of the ever increasing resolution of consumer displays, high quality real-time 3D rendering applications require large amounts of 2D texture data, which in turn require large amounts of storage, memory and bandwidth. One of the major advantages of using compressed texture data is the significant decrease in bandwidth requirements, decreasing texture loading times. Additionally, instead of preloading all the potentially required information, texture data can be streamed progressively at run-time, which is a very common scenario in web-based applications, games and large virtual environments. This paper proposes a new texture streaming system, utilizing both pre-computed and run-time scene analysis, camera prediction and wavelet-based texture compression to provide maximal visual quality within bandwidth and real-time constraints. Texture decoding is done on the GPU, saving both on streaming bandwidth and GPU memory. The pre-computed scene analysis system can perform the run-time analysis at virtually no performance cost in multi-threaded systems. The proposed solution can easily be plugged into existing classical texture mapping solutions, as it features drop-in replacement shaders and re-uses existing render facilities. The wavelet-based streaming system results in PSNR improvements of up to 2 dB when compared to a DXT1-based streaming system.
Keyword:
Texture mapping
Texture streaming
Wavelet transform
Texture compression
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:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
Knocking at the wrong door: Insured workers' inadequate psychiatric care and workers' compensation claims敲错门:受保工人的精神科护理不足与工伤赔偿申请
Insufficient evidence on health literacy amongst Indigenous people with cancer: a systematic literature review癌症患者中土著人群健康素养证据不足:一项系统文献综述
Hydrogen Mobility Europe (H2ME): Vehicle and Hydrogen Refuelling Station Deployment Results欧洲氢能移动 (H2ME): 车辆和加氢站部署结果

