FIRe: Fast Inverse Rendering using Directional and Signed Distance Functions

TL;DR

FIRe introduces a neural scene representation called the directional distance function (DDF) that enables fast, single-evaluation rendering of 3D shapes from depth maps, significantly improving speed and accuracy over existing methods.

Contribution

The paper proposes a novel DDF model combined with a fast reconstruction algorithm, enabling efficient 3D shape reconstruction from depth images with fewer network evaluations.

Findings

Reconstructs 3D shapes more accurately than prior methods.

Achieves over 15 times faster reconstruction per iteration.

Requires only a single network evaluation per camera ray.

Abstract

Neural 3D implicit representations learn priors that are useful for diverse applications, such as single- or multiple-view 3D reconstruction. A major downside of existing approaches while rendering an image is that they require evaluating the network multiple times per camera ray so that the high computational time forms a bottleneck for downstream applications. We address this problem by introducing a novel neural scene representation that we call the directional distance function (DDF). To this end, we learn a signed distance function (SDF) along with our DDF model to represent a class of shapes. Specifically, our DDF is defined on the unit sphere and predicts the distance to the surface along any given direction. Therefore, our DDF allows rendering images with just a single network evaluation per camera ray. Based on our DDF, we present a novel fast algorithm (FIRe) to reconstruct 3D shapes given a posed depth map. We evaluate our proposed method on 3D reconstruction from single-view depth images, where we empirically show that our algorithm reconstructs 3D shapes more accurately and it is more than 15 times faster (per iteration) than competing methods.