HiPR: Hierarchical Progressive Rendering for Immediate Feedback

2026-06-25

AI Summary

Traditional path tracing requires recomputing entire frames upon scene modifications, hindering real-time interactivity. This work proposes a dynamic rendering scheduling algorithm that constructs a hierarchical dependency structure among light paths across pixels and progressively updates them based on perceptual importance: high-priority regions are re-rendered first, while others temporarily reuse historical data. This approach delivers immediate visual feedback without compromising eventual unbiased convergence. Departing from conventional error-driven or temporal reuse strategies, the method introduces a novel scheduling mechanism grounded in light-path dependencies and perceptual priorities, significantly enhancing interaction smoothness and enabling efficient, responsive interactive path tracing.

Abstract

Hierarchical Progressive Rendering (HiPR) is a dynamic render-scheduling algorithm that makes interactive path tracing finally feel real-time. While most renderers recompute the entire frame after any change to the scene, our method updates some of the pixels based on a priority order while keeping the others unchanged. Rather than relying on error-driven or temporal reuse heuristics, it amortizes rendering costs by organizing pixels into a hierarchy of light-path dependencies from changed elements outward, prioritizing by perceptual impact and delivering instant visual feedback, while eventually converging to an unbiased result.

Problem

• interactive path tracing
• real-time feedback
• render scheduling
• progressive rendering
• visual feedback

Innovation

• Hierarchical Progressive Rendering
• dynamic render-scheduling
• path tracing
• perceptual prioritization
• unbiased convergence