High Dynamic Range Compression on Programmable Graphics Hardware

本文介绍了一种用于将高动态范围图像压缩以适应常规显示设备的技术。该技术通过操纵亮度图像的梯度场并减弱大梯度的幅度来保留细节,最终生成的图像能够引发与观察真实场景相似的感受。整个过程建立在可编程图形硬件之上,并利用GPU加速提供快速的动态范围压缩技术。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

    We present a system for compressing high dynamic range images to fit conventional display devices that are only capable of outputting a low dynamic range. In addition to manipulating the gradient field of luminance image by attenuating the large gradients‘ magnitudes, it can preserve fine details, resulting in an image which provokes the same responses as someone would have viewing the scene in the real world. Specifically, with the whole process built on programmable graphics hardware, we present an efficient algorithm based on GPU acceleration and provide a fast dynamic range compression technique. Furthermore, we describe a framework for rendering high dynamic range images in real time. It not only can be used in image based tone mapping but also is able to be a core technique in interactive graphics applications.

     OK, After Image Processing, High Dynamic Range Compression, Poisson Equation, Programmable Graphics Hardware...I've implemented a demo for GPUGHDRC, which is based on Supra Engine.  For MS Confidential, I can not supply the demo.
       All the algorithms and details of implementation are described in my paper “High Dynamic Range Compression on Programmable Graphics Hardware”(Appeared in Microcomputer Development, Issue 9, 2005).
       Slides: 
GPUGHDRC_slides.pdf

Detail:http://www.xf-utpcb.com/xiaop/MyProjects/ghdrc.htm

Screen Shot:

GHDRC with parameters in tweaker

GHDRC with parameters in tweaker

work on HDR memorial scène

work on HDR memorial scène

For the detail,you can see http://www.xf-utpcb.com/xiaop/MyProjects/ghdrc.htm

转载于:https://www.cnblogs.com/xiaop/archive/2006/04/17/377213.html

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值