FIRe: Fast Inverse Rendering using Directional and Signed Distance Functions
This addresses the speed limitation in 3D reconstruction for applications like single-view depth imaging, though it is incremental as it builds on existing neural implicit representations.
The paper tackles the computational bottleneck in neural 3D implicit representations by introducing a directional distance function (DDF) that enables rendering with a single network evaluation per camera ray, resulting in more than 15 times faster reconstruction per iteration and improved accuracy compared to competing methods.
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.