» 您尚未登录:请 登录 | 注册 | 标签 | 帮助 | 小黑屋 |


 42 123
发新话题
打印

[新闻] 农企公布FSR(FidelityFX Super Resolution),最低支持RX 500/Geforce 1000系列



https://www.bilibili.com/video/BV13K4y137Xt

具体画质怎么样还得等6月22日出了再说,而不是看这个压缩过的视频
不过我认为是比不过DLSS 2.0
原因很简单,它居然支持RX 500,甚至Geforce 1000系列,这些都没有Tensor Core……
首发游戏会有40个,但也不是完美兼容,比如地铁逃离就说了引擎不能用这个

当然这个技术不是完全没用,所有缺乏Tensor Core的显卡,包括N家的老卡,A家的这些主机,都可以用了
只是,这不是唯一的方案

https://www.amd.com/en/technolog ... fx-super-resolution
https://www.pcgamer.com/amd-fide ... ement-release-date/

[ 本帖最后由 Nemo_theCaptain 于 2021-6-1 18:17 编辑 ]


TOP

posted by wap, platform: iPhone
真的吗

AMD开发人员重点提了XSS,在AMD FSR 功能打开状态下,《战争机器 5》从原升2560x1600分辨率经过FSR智能采样重建提升至 3840x2160分辨率,仅仅增加部分功耗,但帧数零损失。“在XSS上,打开FSR之后观感上看起来超过原生1800P棋盘渲染4K的效果,帧数毫无波动,在4K电视上体验极好,该技术更新提升了该主机的视觉体验与性价比。”



TOP

引用:
原帖由 DarthVadar 于 2021-6-1 16:20 发表
posted by wap, platform: iPhone
真的吗

AMD开发人员重点提了XSS,在AMD FSR 功能打开状态下,《战争机器 5》从原升2560x1600分辨率经过FSR智能采样重建提升至 3840x2160分辨率,仅仅增加部分功耗,但帧数零损失 ...
这说的是比棋盘渲染强,又不是比DLSS 2.0强,就算是真的,也不算惊世骇俗

[ 本帖最后由 Nemo_theCaptain 于 2021-6-1 16:35 编辑 ]


TOP

期待农村企业发功!
我就说了什么DLSS不过就是软件层的,你能编人就不能了?连花x都能抄出个蒙哄。

TOP

posted by wap, platform: iPhone
总比没有好,让短板没那么短

TOP

posted by wap, platform: 小米NOTE
类似的技术永远不嫌多,amd yes

TOP

posted by wap, platform: 小米
主机需要这个

TOP

对游戏机肯定是有意义的

TOP

posted by wap, platform: Android
只要主机能用,这东西普及不是问题

TOP

不错哦,关键是老卡也能用,现在买不到显卡,老卡还能多用一阵子

TOP

posted by wap, platform: Android
完全不用机器学习的超采样方法。效果怎么样确实比较打问号,不过开源,如果真的有潜力估计社区还是能捣鼓出些明堂的的。对硬件固化的主机真是重大利好

老黄搞硬件支持,AMD搞软件算法

TOP

posted by wap, platform: Android
想不明白为啥500系列可以,400系列不行

TOP

posted by wap, platform: Android
引用:
原帖由 @bazinga  于 2021-6-1 21:51 发表
完全不用机器学习的超采样方法。效果怎么样确实比较打问号,不过开源,如果真的有潜力估计社区还是能捣鼓出些明堂的的。对硬件固化的主机真是重大利好

老黄搞硬件支持,AMD搞软件算法
据发布的专利说是用了深度学习

本帖最后由 旨旨xx 于 2021-6-1 22:21 通过手机版编辑

TOP

posted by wap, platform: iPhone
https://www.anandtech.com/show/16723/amd-formally-unveils-fidelityfx-super-resolution-open-source-game-upscaling

看了 anandtech 的文章,我对 fsr 第一版没啥指望了,还是基于当前帧的缩放,没像 dlss2.0 一样用到运动矢量

TOP

posted by wap, platform: iPhone
And, to drop into op-ed mode, this is where AMD has me a bit worried. In our pre-briefing with AMD, the company did confirm that FSR is going to be a purely spatial upscaling technology; it will operate on a frame-by-frame basis, without taking into account motion data (motion vectors) from the game itself.

For GPU junkies, many of you will recognize this as a similar strategy to how NVIDIA designed DLSS 1.0, which was all about spatial upscaling by using pre-trained, game-specific neural network models. DLSS 1.0 was ultimately a failure – it couldn’t consistently produce acceptable results and temporal artifacting was all too common. It wasn’t until NVIDIA introduced DLSS 2.0, a significantly expanded version of the technology that integrated motion vector data (essentially creating Temporal AA on steroids), that they finally got DLSS as we know it in working order.

Given NVIDIA’s experience with spatial-only upscaling, I’m concerned that AMD is going to repeat NVIDIA’s early mistakes. Spatial is a lot easier to do on the backend – and requires a lot less work from developers – but the lack of motion vector data presents some challenges. In particular, motion vectors are the traditional solution to countering temporal artifacting in TAA/DLSS, which is what ensures that there are no frame-by-frame oddities or other rendering errors from moving objects. Which is not to say that spatial-only upscaling can’t work, only that, if it’s competitive in image quality with DLSS, that would be a big first for AMD.

原文

不知道实际效果和 dlss1.0 比怎么样

TOP

 42 123
发新话题
     
官方公众号及微博