PRIF: Primary Ray-based Implicit Function

TL;DR

PRIF introduces a novel implicit shape representation based on oriented rays, enabling efficient shape extraction and differentiable rendering without sphere-tracing, and demonstrates versatility across multiple shape and rendering tasks.

Contribution

The paper proposes PRIF, a new ray-based implicit function that improves efficiency and versatility over traditional SDF-based methods for shape representation and rendering.

Findings

Enables direct surface hit point prediction from input rays.

Achieves efficient shape extraction without sphere-tracing.

Successfully applied to shape modeling, completion, inverse rendering, and neural rendering.

Abstract

We introduce a new implicit shape representation called Primary Ray-based Implicit Function (PRIF). In contrast to most existing approaches based on the signed distance function (SDF) which handles spatial locations, our representation operates on oriented rays. Specifically, PRIF is formulated to directly produce the surface hit point of a given input ray, without the expensive sphere-tracing operations, hence enabling efficient shape extraction and differentiable rendering. We demonstrate that neural networks trained to encode PRIF achieve successes in various tasks including single shape representation, category-wise shape generation, shape completion from sparse or noisy observations, inverse rendering for camera pose estimation, and neural rendering with color.