Next Event Backtracking

TL;DR

This paper introduces a novel method combining path tracing and photon transport using last segment backtracking, enhanced by a lock-free sparse octree for efficient density estimation, improving rendering in complex light-material scenarios.

Contribution

It proposes a new hybrid approach that leverages the last segment of path tracing as the first of photon paths, improving light transport efficiency in challenging scenes.

Findings

Outperforms Vertex Connection and Merging in specific scenarios.

Uses a lock-free sparse octree for fast density estimation.

Enhances photon guidance towards important regions.

Abstract

In light transport simulation, challenging situations are caused by the variety of materials and the relative length of path segments. Path Tracing can handle many situations and scales well to parallel hardware. However, it is not able to produce paths which have a smooth surface in connection with a small light source. Here, photon transports perform superior, which can be ineffective if the smooth object is small compared to the scene size. We propose to use the last segment of a Path Tracer path as the first segment of a photon path. As a result, the strengths of next event estimation are inherited by the photon transport and photons are guided toward the regions where they are most useful. To that end, we developed a lock-free sparse octree, which we use for fast and robust density estimates. Summarizing, the new method can outperform state of the art algorithms like Vertex Connection and Merging in certain scenarios.