HashPoint: Accelerated Point Searching and Sampling for Neural Rendering

TL;DR

HashPoint combines rasterization and ray marching to accelerate neural rendering, achieving faster rendering speeds while maintaining high quality, by efficient point searching and adaptive sampling.

Contribution

This paper introduces HashPoint, a novel method that integrates rasterization and ray marching for efficient point searching and sampling in neural rendering.

Findings

Significant speed-up in rendering times for state-of-the-art methods

Maintains or improves rendering accuracy on synthetic and real datasets

Efficient point organization using hash tables enhances search speed

Abstract

In this paper, we address the problem of efficient point searching and sampling for volume neural rendering. Within this realm, two typical approaches are employed: rasterization and ray tracing. The rasterization-based methods enable real-time rendering at the cost of increased memory and lower fidelity. In contrast, the ray-tracing-based methods yield superior quality but demand longer rendering time. We solve this problem by our HashPoint method combining these two strategies, leveraging rasterization for efficient point searching and sampling, and ray marching for rendering. Our method optimizes point searching by rasterizing points within the camera's view, organizing them in a hash table, and facilitating rapid searches. Notably, we accelerate the rendering process by adaptive sampling on the primary surface encountered by the ray. Our approach yields substantial speed-up for a range of state-of-the-art ray-tracing-based methods, maintaining equivalent or superior accuracy across synthetic and real test datasets. The code will be available at https://jiahao-ma.github.io/hashpoint/.