Microsoft, Tencent and Baidu are adopting NVIDIA CV-CUDA for computer vision AI. NVIDIA CEO Jensen Huang highlighted work in content understanding, visual search and deep learning Tuesday as he announced the beta release for NVIDIA's CV-CUDA—an open-source, GPU-accelerated library for computer vision at cloud scale. "Eighty percent of internet traffic is video, user-generated video content is driving significant growth and consuming massive amounts of power," said Huang in his keynote at NVIDIA's GTC technology conference. "We should accelerate all video processing and reclaim the power."

CV-CUDA promises to help companies across the world build and scale end-to-end, AI-based computer vision and image processing pipelines on GPUs. The majority of internet traffic is video and image data, driving incredible scale in applications such as content creation, visual search and recommendation, and mapping. These applications use a specialized, recurring set of computer vision and image-processing algorithms to process image and video data before and after they're processed by neural networks.

BenQ introduced the PD2506Q, a 25-inch monitor for creative professionals. The monitor offers several features useful for pros, such as 10bpc color, AQColor calibration, a "Darkroom" mode that adjusts settings to an image post-processing environment, Design and CAD-CAM modes that appear to add certain edge anti-aliasing to the screen; etc. Its key specs include WQHD (1440p) resolution, DisplayHDR 400 / HDR10 readiness, 178° viewing angles, and 350 cd/m² brightness. A stand-out feature is its set of inputs, which include HDMI 2.0, DisplayPort 1.4, and USB type-C. The monitor supports type-C for display input (as in DisplayPort passthrough), USB upstream input, and power delivery (USB-PD 65 W needed). It also supports daisy-chaining of up to two monitors. If you lack a USB-PD power source, you can just use the included power brick.

AMD today in a blog post announced several updates to the FidelityFX Super Resolution (FSR) technology, its performance enhancement rivaling NVIDIA DLSS, which lets gamers dial up performance with minimal loss to image quality. To begin with, the company released the source code of the technology to the public under its GPUOpen initiative, under the MIT license. This makes it tremendously easy (and affordable) for game developers to implement the tech. Inspecting the source, we find that FSR relies heavily on a multi-pass Lanczos algorithm for image upscaling. Next up, we learn that close to two dozen games are already in the process of receiving FSR support. Lastly, it's announced that Unity and Unreal Engine support FSR.

AMD broadly detailed how FSR works in its June 2021 announcement of the technology. FSR sits within the render pipeline of a game, where an almost ready lower-resolution frame that's been rendered, tone-mapped, and anti-aliased, is processed by FSR in a two-pass process implemented as a shader, before the high-resolution output is passed on to post-processing effects that introduce noise (such as film-grain). HUD and other in-game text (such as subtitles), are natively rendered at the target (higher) resolution and applied post render. The FSR component makes two passes—upscaling, and sharpening. We learn from the source code that the upscaler is based on the Lanczos algorithm, which was invented in 1979. Media PC enthusiasts will know Lanczos from MadVR, which has offered various movie upscaling algorithms in the past. AMD's implementation of Lanczos-2 is different than the original—it skips the expensive sin(), rcp() and sqrt() instructions and implements them in a faster way. AMD also added additional logic to avoid the ringing effects that are often observed on images processed with Lanczos.

NVIDIA updated the NVIDIA Broadcast software to version 1.2, to include even more features that the company claims can transform any room into a home-studio. The latest version can remove room echo, audio reverb/echo caused by the walls of the room, to put out clear voice. It can also detect and remove certain kinds of pet noises from the background, so your doggo doesn't mess with an important call at work. Lastly, the video post-processing tech has been improved to reduce video noise stemming from sub-optimal lighting conditions or low web-cam resolutions. NVIDIA Broadcast can also be integrated with popular streaming platforms such as OBS, AVerMedia, and Notch.

Intel is revisiting the concept of asymmetric multi-GPU introduced with DirectX 12. The company posted an elaborate technical slide-deck it originally planned to present to game developers at the now-cancelled GDC 2020. The technology shows promise because the company isn't insulting developers' intelligence by proposing that the iGPU lying dormant be made to shoulder the game's entire rendering pipeline for a single-digit percentage performance boost. Rather, it has come up with innovating augments to the rendering path such that only certain lightweight compute aspects of the game's rendering be passed on to the iGPU's execution units, so it has a more meaningful contribution to overall performance. To that effect, Intel is on the path of coming up with SDK that can be integrated with existing game engines.

Microsoft DirectX 12 introduced the holy grail of multi-GPU technology, under its Explicit Multi-Adapter specification. This allows game engines to send rendering traffic to any combinations or makes of GPUs that support the API, to achieve a performance uplift over single GPU. This was met with lukewarm reception from AMD and NVIDIA, and far too few DirectX 12 games actually support it. Intel proposes a specialization of explicit multi-adapter approach, in which the iGPU's execution units are made to process various low-bandwidth elements both during the rendering and post-processing stages, such as Occlusion Culling, AI, game physics, etc. Intel's method leverages cross-adapter shared resources sitting in system memory (main memory), and D3D12 asynchronous compute, which creates separate processing queues for rendering and compute.

De-noising is a vital post-processing component of ray-traced images, as it eliminates visual noise generated by too few rays intersecting pixels that make up an image. In an ideal world, a ray should hit every pixel on the screen, but in the real world, computing hasn't advanced enough to do that in reasonable/real-time. Denoising attempts to correct and reconstruct such images. Intel today launched a free Open Image Denoise (OIDN) library for ray-tracing.

Governed by the Apache 2.0 license, OIDN is part of Intel Rendering framework. From the looks of it, the library is CPU-based, and leverages 64-bit x86 CPU (scaling with multi-core and exotic instruction-sets), to de-noise images. Intel says OIDN works on any device with a 64-bit x86 processor (with at least SSE4.2 instruction-set), although it can take advantage of AVX2 and AVX-512 to speed things up by an order of magnitude. The closest (and closed) alternative to OIDN would be NVIDIA's AI De-noiser. NVIDIA "Turing" GPUs use a combination of ad-hoc deep-learning neural networks and GPU compute to de-noise. You can freely access OIDN on Intel's Git.

Generic post-processing injector, ReShade, which offers SMAA anti-aliasing, screen space ambient occlusion, depth of field, and many other effects, has been updated to version 4.0. More than just a version update the ReShade FX compiler has received a complete overhaul having been made fully standalone as of this release. These changes bring performance improvements, better error recovery, improved support for code features, and even opens up the ability to add Vulkan support since it can now generate HLSL, GLSL, and SPIR-V. With a change-log packed with enhancements changes and new features, Crosire, the author also reworked the UI. Not only can the new UI be customized by the user, but it also includes new features such as an in-game code editor and texture preview.

While it should be noted that due to the compiler change some effects may no longer compile or work properly in version 4.0. However, these effects just need to be updated by their authors to work with the latest release. Going forward it is likely smaller revisions and updates will be forthcoming with a version 4.0.1 already having surfaced with further fixes. Sadly, even with these quick fixes, teething issues continue beyond the few broken effects by other authors. Some games like Diablo 2 and Arma 3 are proving problematic for some users of the latest ReShade version. Even so, with further updates should see these issues resolved, however for those enjoying those two games, in particular, can roll back to 3.4.1 which remains a fairly stable release.The Change-log follows.