you have good eyes


Iray AI with Deep Learning

Here is the demo content that I have created to showcase NVIDIA’s new denoising technology that utilizes deep learning. When raytracing photorealistic imagery, millions of rays are calculating each pixel of an image. This refines over time, but with deep learning training sets, the AI can simulate what each pixel will become refining the image at much faster speeds. The side by side comparisons shows the effect of the Iray AI with just moments of render time on NVIDIA GPUs. These images were rendered on 2 QUADRO GP100s.

Make sure to click on each image to see at 4K resolution.


GTC 2017: Deep Learning for Ray Tracing

Jensen now shows a slide titled Deep Learning for Ray Tracing. He describes how Deep Learning can be applied to the incredibly computationally demanding task of following photons around a simulated scene. It allows us to use AI to fill in information.

He shows a pair of simulated Mercedes SLK 350s, one being rendered without deep learning take some time to fully resolve in photo -realistic detail. With deep learning it can do this much faster. Deep learning based auto encoders work incredibly fast. In a matter of seconds, the full scene is rendered, including the reflection of trees, clouds and other objects in the larger scene.

Iray Plug-in UI in 4k

Here are a few UI layouts of Iray in action! Click to see in 4k…

IFMAX UI InteriorSplitLevel


Iray VR – Bank of England


Iray for 3ds Max goes live!

Welcome to the Iray for 3ds Max – Content Creation Series.  Watch the video introduction here or click on any of the following images to link to the YouTube Channel containing all of the following videos topics. We hope you find these tips and techniques helpful as you learn more about interactive rendering in Iray for 3ds Max.

Check out how this new plugin, Iray for 3ds Max, harnesses interactivity and scalability to deliver the full power of physically based rendering. Take a quick tour of the intuitive workflow that takes advantage of MDL material creation and exchange to maximize your productivity with immediate visual feedback during scene development and lighting.

IFMAX_00_InteractiveRendering_w950We hope you’ve been enjoying working with the Iray for 3ds Max. Starting today, we’ll be sharing some tips and techniques to aid with your workflow. Check out our first video on interactive rendering and learn how to dynamically make scene updates, such as assigning materials, camera setup, and swapping HDR image based lighting.

IFMAX_01_PhysicalLighting_w950We know the importance of lighting your designs. Let’s take a look at how to dynamically setup your lights and adjust parameters with interactive feedback. We’ll take a look at the best practices to maintain a physically accurate workflow with the Physical Sky, IBL, and IES profiles. And like a digital photographer, learn how to tweak the final look with real-time edits to the camera tonemapping.

IFMAX_02_CreatingMaterialsWithLayers_w950The Iray for 3ds Max plugin comes preloaded with a series of real world material examples.  Use the predefined materials to effortlessly build a variety physically based materials.  With this unique layering system, add additional material coatings and scratches to design your desired surface appearance.

IFMAX_03_ContextualMaterialEditing_w950Let’s take a look at how to utilize Material Override to review real world material examples in the context of a furniture design. We’ll quickly browse through a catalog of physically based materials that are free to download from the advanced rendering forum. Once we have selected a variety of materials, we can then build upon them with layers for an interactive design review.

IFMAX_04_IrayDepthOfField_w950We’d like to share a few techniques to ensure efficient workflow with precise focus on your subject matter. Learn how to interact with Iray (in-camera) Depth of Field to add visual clarity and depth to your rendered imagery. Use real world camera techniques to ensure a tightly focused subject using standard 3ds Max tools.


Stay tuned for more…!

Image Based Lighting at GTC

One of the surprises for the Iray presentation was to capture an IBL of the GTC keynote stage.  This was accomplished by taking a series of photographs and stitching them together to create a spherical image.  By mapping this image composite to the inside of a dome, it was used to cast light, reflection, and shadow on the car model.  Simply put, the car is 3D CAD data and the background is a composite photograph that simulates the car on stage.




Posted by Jay Axe