TechWatch

AMD introduces neural ray tracing

NIF is a significant departure from traditional BVH-based ray tracing.

Jon Peddie

Monte Carlo ray tracing, vital for photorealistic imagery, relies on ray casting and BVHs for acceleration. However, BVH traversal is irregular, hindering GPU performance despite specialized hardware. In contrast, neural networks offer GPU-friendly, regular computations. This raises the question: Could neural networks replace BVH traversal? Researchers are exploring this, aiming to leverage neural networks’ strengths. Innovations like the Neural Intersection Function seek to overcome BVH limitations, potentially revolutionizing real-time and offline ray tracing by offering a more efficient alternative for GPU architectures.The Monte Carlo process has been the foundation of physically accurate ray tracing for simulating complex light transport in 3D environments
...

Enjoy full access with a TechWatch subscription!

TechWatch is the front line of JPR information gathering service, comprising current stories of interest to the graphics industry spanning the core areas of graphics hardware and software, workstations, gaming, and design.

A subscription to TechWatch includes 4 hours of consulting time to be used over the course of the subscription.

Already a subscriber? Login below

This content is restricted

Subscribe to TechWatch