Iray - with AI Denoising .....

Here's an interesting article on iRay with AI - by Phil Miller - from May, 2017 (I looked into this after Dennis (JAV) made mention of 'AI denoising' on another thread)

How Iray Interactive Denoising Works

Existing algorithms for high-quality denoising consume seconds to minutes per frame, which makes them impractical for interactive applications.

By predicting final images from only partly finished results, Iray AI produces accurate, photorealistic models without having to wait for the final image to be rendered.

Designers can iterate on and complete final images 4x faster, for a far quicker understanding of a final scene or model. The cumulative time savings can significantly accelerate a business’s go-to-market plans.

To achieve this, NVIDIA researchers and engineers turned to a class of neural networks called an autoencoder. Autoencoders are used for increasing image resolution, compressing video and many other image processing algorithms.

Using the NVIDIA DGX-1 AI supercomputer, the team trained a neural network to translate a noisy image into a clean reference image. In less than 24 hours, the neural network was trained using 15,000 image pairs with varying amounts of noise from 3,000 different scenes. Once trained, the network takes a fraction of a second to clean up noise in almost any image — even those not represented in the original training set.

With Iray, there’s no need to worry about how the deep learning functionality works. We’ve already trained the network and use GPU-accelerated inference on Iray output. Creatives just click a button and enjoy interactivity with the improved image quality with any Pascal or better GPU.

Iray deep learning functionality will be included with the Iray SDK we supply to software companies, and exposed in Iray plugin products we produce later this year. We also plan to add an AI mode to NVIDIA Mental Ray. We expect renderers of many kinds to adopt this technology. The basis of this technique will be published at the ACM SIGGRAPH 2017 computer graphics conference in July.

Source: https://blogs.nvidia.com/blog/2017/05/10/ai-for-ray-tracing/

--------------------------------------------------------------------------------------------------------------------------------------------------------

Please be patient with me ..... I don't always 'get it' the first time 'round - not even the 2nd time! :( - yikes! ...

● MSI GT72VR Laptop, i7 7700HQ 4-Core 3.8 GHz 16GB RAM; Nvidia 1070, 8GB Vram ● iClone-7.93 ● 3DXChange Pipeline 7.81 ● CC-3 Pipeline 3.44 ● Live Face ● HeadShot ● Brekel Pro-Body ● Popcorn FX ● iRAY ● Kinect V2 ● DaVinci Resolve17 ● Mixcraft 8.1

Author	Message
sonic7	sonic7 Posted 8 Years Ago
Distinguished Member Group: Forum Members Last Active: 3 Years Ago Posts: 1.7K, Visits: 19.4K	Here's an interesting article on iRay with AI - by Phil Miller - from May, 2017 (I looked into this after Dennis (JAV) made mention of 'AI denoising' on another thread) How Iray Interactive Denoising Works Existing algorithms for high-quality denoising consume seconds to minutes per frame, which makes them impractical for interactive applications. By predicting final images from only partly finished results, Iray AI produces accurate, photorealistic models without having to wait for the final image to be rendered. Designers can iterate on and complete final images 4x faster, for a far quicker understanding of a final scene or model. The cumulative time savings can significantly accelerate a business’s go-to-market plans. To achieve this, NVIDIA researchers and engineers turned to a class of neural networks called an autoencoder. Autoencoders are used for increasing image resolution, compressing video and many other image processing algorithms. Using the NVIDIA DGX-1 AI supercomputer, the team trained a neural network to translate a noisy image into a clean reference image. In less than 24 hours, the neural network was trained using 15,000 image pairs with varying amounts of noise from 3,000 different scenes. Once trained, the network takes a fraction of a second to clean up noise in almost any image — even those not represented in the original training set. With Iray, there’s no need to worry about how the deep learning functionality works. We’ve already trained the network and use GPU-accelerated inference on Iray output. Creatives just click a button and enjoy interactivity with the improved image quality with any Pascal or better GPU. Iray deep learning functionality will be included with the Iray SDK we supply to software companies, and exposed in Iray plugin products we produce later this year. We also plan to add an AI mode to NVIDIA Mental Ray. We expect renderers of many kinds to adopt this technology. The basis of this technique will be published at the ACM SIGGRAPH 2017 computer graphics conference in July. Source: https://blogs.nvidia.com/blog/2017/05/10/ai-for-ray-tracing/ -------------------------------------------------------------------------------------------------------------------------------------------------------- Please be patient with me ..... I don't always 'get it' the first time 'round - not even the 2nd time! :( - yikes! ... ● MSI GT72VR Laptop, i7 7700HQ 4-Core 3.8 GHz 16GB RAM; Nvidia 1070, 8GB Vram ● iClone-7.93 ● 3DXChange Pipeline 7.81 ● CC-3 Pipeline 3.44 ● Live Face ● HeadShot ● Brekel Pro-Body ● Popcorn FX ● iRAY ● Kinect V2 ● DaVinci Resolve17 ● Mixcraft 8.1

Iray - with AI Denoising .....