Neural Frame Extrapolation for Selective Ray-Traced Rendering

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Cloud gaming experiences are hindered by the high computational demands of rendering high-resolution, high-frame-rate visuals with ray tracing, leading to frame rendering delays and dropped frames, which degrade user experience.

Innovation Solution

Implement neural frame extrapolation to predict the next frame and generate a per-pixel confidence map, focusing compute resources on regions below an acceptable threshold, thereby optimizing ray tracing within limited budgets.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If ray tracing is used to increase photo realism, then visual quality is improved, but computational resource demand increases

Engineering Contradiction:

Improvevisual qualityVSAvoidcomputational resource demand

Core Design Contradiction:

Manufacturing precisionVSUse of energy by moving object

Solution Approach 1:

The patent applies local quality by differentiating treatment across different regions of the frame. A confidence map is generated to identify regions where neural frame extrapolation is reliable versus regions requiring full ray tracing. This allows ray tracing to be applied selectively only to uncertain regions rather than uniformly across the entire frame, optimizing the balance between visual quality and computational resource usage.

Inventive Principle:

Principle #3Local quality

2Manufacturing precision

If high resolution/high frame rate rendering is implemented, then user experience is improved, but frame rendering time increases

Engineering Contradiction:

Improverendering qualityVSAvoidframe rendering time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent implements preliminary action by performing neural frame extrapolation in advance to generate predicted frames and confidence maps before final rendering. This allows the system to pre-identify which regions require expensive ray tracing operations, enabling proactive resource allocation and reducing overall frame rendering time by avoiding unnecessary full-frame ray tracing.

Inventive Principle:

Principle #10Preliminary action

3Ease of operation

If cloud gaming is used to access games on client devices, then device requirements are reduced, but network dependency increases

Engineering Contradiction:

Improvedevice accessibilityVSAvoidnetwork dependency

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent applies partial action by implementing a hybrid rendering approach that combines neural frame extrapolation with selective ray tracing. This allows cloud gaming services to deliver high-quality visuals while reducing the computational burden on both cloud and client devices. The confidence map mechanism ensures that neural predictions are used only where reliable, maintaining visual quality without excessive network bandwidth requirements.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12548204B2Neural frame extrapolation rendering mechanism

Publication Date: 2026.02.10 INTEL CORP

AI summary

A mechanism is described for image frame rendering. An apparatus of embodiments, as described herein, includes one or more processors to receive a plurality of past image frames including a plurality of pixels, receive a predicted optical flow, generate a predicted frame and a confidence map associated with the predicted frame based on the plurality of past image frames and the predicted optical flow, render a first set of the plurality of pixels in the predicted frame based on the confidence map and adding the rendered pixels to the predicted frame to generate a final frame.