I'm incredibly excited and honored to share that Intel Open Image Denoise will receive an Academy SciTech Award! After Intel Embree, this is the second open source library from the Intel Rendering Toolkit to be awarded by the Academy. #Oscars#IamIntel
https://t.co/QCeIXDX50q
Blender 4.2 LTS is out with the latest Intel Open Image Denoise 2.3, which significantly improves quality in High Quality + Accurate Prefilter mode, adds a new Fast Quality mode for even faster previews, enables GPU denoising for CPU renders and AMD GPU support as well. #IamIntel
Intel Open Image Denoise 2.2.0 is out! It improves image quality and CPU performance, adds support for Intel Meteor Lake GPUs, Apple GPUs (via Metal) and all ARM64 CPUs, removes dependency on CUDA Runtime (switches to Driver API), and more! https://t.co/XDwtJdE8tD #IamIntel
Really proud that our Grenoble Graphics team won the 1st and 2nd Best Paper Awards at @HPG_Conf 2023.
@thomasdeliot and @_Laurent won the 1st place with their real-time glints
Jonathan Dupuy and @Auzaiffe
won the 2nd place with their GGX VNDF sampling
https://t.co/4v5L9aZrqg
Intel Graphics Research is excited to share our contribution across SIGGRAPH, EGSR, HPG, and EG this summer. Low-energy path tracing, generative AI, neural graphics and more!
https://t.co/RMFbOrzXhK
Amazing work of our researchers and collaborators.
Nanite rasterizes virtualized geometry by selecting ~20 million triangles with appropriate LOD each frame.
Carsten Benthin and I wrote a @HPG_Conf paper on how to build a BVH for these 🔺s instead. Since they are already clustered, the build is 10x faster!
https://t.co/yUMFIUYZLo
When @_Laurent and I started learning about diffusion models, we were puzzled by the amount of jargon and concepts.
So, we derived a model from scratch with our own graphics-people intuitions. Simple derivation, simple implementation, SOTA quality.
https://t.co/o9V6lbNl1o
Intel Open Image Denoise 2.0 has been released! It adds support for Intel GPUs (Arc, Data Center GPU Flex and Max Series, integrated GPUs), NVIDIA GPUs, and AMD GPUs, on Windows and Linux. Same image quality as on CPUs but *much* faster! https://t.co/WHyAIhYFBm #iamintel
I'm thrilled to share our #SIGGRAPH2023 paper “Neural Prefiltering for Correlation-Aware Levels of Detail” in which we introduce a novel framework for compressed storage of high-detail geometry and appearance. (with @alphanew, @Kaplanyan, @lingqi_yan, and Philipp Slusallek)
Would you like to learn path tracing over the holidays? I created a workshop with 76 minutes of video presentation. Solve the @ShaderToy exercises as you watch, and you will have written your own ray and path tracer!
Brought to you by @IntelGraphics.
https://t.co/uDFobGMNvb
Looking for a 2023 internship? Intel Graphics Research is hiring in graphics and content creation/generation to advance Intel GPUs. Example topics are neural rendering, distributed rendering, path tracing, differentiable rendering, perceptual graphics 1/..
If you are porting your CPU renderer to GPU, we are glad to introduce Intel Max datacenter GPUs with 128GB RAM and hardware ray tracing. Easy to port your CPU codebase. It can run an unchanged Disney Moana production scene interactively with curves, instances etc.
Sebastian Herholz’s talk, Follow the Light: Introducing Path Guiding in Cycles is available! It is a great intro to PG and how/when to use it in Blender. It uses Intel OpenPGL - also open source. #OneAPI#Intel#PathGuiding#PathTracing#blender#bcon2022 https://t.co/oyccqT7Th4
We are happy to share our new @siggraph paper Rendering Neural Materials on Curved Surfaces, which enables the use of neural materials on arbitrary geometry.
https://t.co/RMS0HTENTX
@BattleAxeVR@Kaplanyan We have comparison to rendering at 720p, 1440p and 720p with UE4 denoiser to 1440p using XeSS. You can find more details in the publication (Sec 4.14 and Fig 9).
Neural supersampling methods like @Intel XeSS are already popular in games, while neural denoisers remain too costly.
Our @HPG_Conf 2022 paper, led by @mt_manu, trains a single network with multi-resolution kernel prediction to perform both tasks at once.
https://t.co/I6SbEaYo3U
I'm excited to share that Intel #Embree and Intel #OpenImageDenoise are running in real time on a pre-production ray tracing capable Xe GPU, at the same quality as on CPUs, in this path tracing demo (1080p, 1 spp) from Intel Architecture Day: https://t.co/1JWCAhM5rB #IamIntel
Intel Embree has been awarded a Sci-Tech Technical Achievement Award by @TheAcademy! It's a great honour for us, thank you @TheAcademy! Also, many thanks to @jamesljeffers and @j_c_inPDX at Intel for their leadership and support throughout the years! https://t.co/BBnKMholYf