混世魔头
查看详细资料
TOP
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
原帖由 @huzhiyangqaz 于 2021-6-1 22:35 发表 And, to drop into oped mode, this is where AMD has me a bit worried. In our prebriefing with AMD, the company did confirm that FSR is going to be a purely spatial upscaling technology; it will operate on a framebyframe 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 pretrained, gamespecific 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 spatialonly 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 framebyframe oddities or other rendering errors from moving objects. Which is not to say that spatialonly 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
原帖由 @huzhiyangqaz 于 2021-6-2 01:06 发表 原文后面有张 amd 官方放出的 1060 开 fsr 的对比图，仅从这张图来看的话，fsr 静态表现估计不会太好 看正式公布时动态表现怎么样了
原帖由 @mitsuna 于 2021-6-2 08:30 发表 太模糊了 感觉不如棋盘格
原帖由 @Nemo_theCaptain 于 2021-6-4 21:44 发表 在Computex期间，AMD全球副总裁Radeon游戏产品部总经理Scott Herkelman表示，FidelityFX Super Resolution（FSR）将支持众多Radeon RX 500 / RX Vega / RX 5000 / RX 6000系列的显卡，包括基于Vega架构的APU也会得到支持。不少用户可能会疑惑，为什么与Radeon RX 500系列基本一致的Radeon RX 400系列会被排除。 AMD负责人Mickey Molad表示，AMD正在更新与FidelityFX Super Resolution相兼容的AMD显卡列表，届时名单里会包括Radeon RX 480 / RX 470两款显卡，预计网站上的信息很快会得到更新。 不过声明里并没有确认，像Radeon RX 550 / RX 560这样的显卡是否也能支持FidelityFX Super Resolution。另外作为DirectX12、DirectX11和Vulkan API支持的跨平台技术，即便是英特尔的集成显卡或英伟达的入门级GPU想要支持，应该也是可以的。英特尔高级副总裁、首席架构师兼架构、图形与软件部门总经理Raja Koduri在其推特账户上表示了对FidelityFX Super Resolution产生兴趣，未来有可能会用在即将到来的XeHPG架构GPU上。 FidelityFX Super Resolution的推出引起了不少人的讨论，证明这项技术备受期待。不过也有人提出了疑虑，官方的视频和图片显示，在启用FidelityFX Super Resolution以后，图像的质量有比较明显的下降。虽然不同游戏引擎或不同架构的GPU其工作情况可能有所区别，或许还要考虑到AMD会与自己其他图形技术一起使用，不过已引起忧虑。最近AMD与Epic展开合作，在虚幻引擎5上为AMD的GPU进行优化，暂时看来，动态中的画面效果也并不那么好。 https://www.expreview.com/79243.html
原帖由 @pyromania 于 2021-6-5 00:15 发表 正在观望显卡，N卡目前溢价仍然太高，要不要入5700xt战未来？
