Volume Rendering of Neural Implicit Surfaces

by   Lior Yariv, et al.

Neural volume rendering became increasingly popular recently due to its success in synthesizing novel views of a scene from a sparse set of input images. So far, the geometry learned by neural volume rendering techniques was modeled using a generic density function. Furthermore, the geometry itself was extracted using an arbitrary level set of the density function leading to a noisy, often low fidelity reconstruction. The goal of this paper is to improve geometry representation and reconstruction in neural volume rendering. We achieve that by modeling the volume density as a function of the geometry. This is in contrast to previous work modeling the geometry as a function of the volume density. In more detail, we define the volume density function as Laplace's cumulative distribution function (CDF) applied to a signed distance function (SDF) representation. This simple density representation has three benefits: (i) it provides a useful inductive bias to the geometry learned in the neural volume rendering process; (ii) it facilitates a bound on the opacity approximation error, leading to an accurate sampling of the viewing ray. Accurate sampling is important to provide a precise coupling of geometry and radiance; and (iii) it allows efficient unsupervised disentanglement of shape and appearance in volume rendering. Applying this new density representation to challenging scene multiview datasets produced high quality geometry reconstructions, outperforming relevant baselines. Furthermore, switching shape and appearance between scenes is possible due to the disentanglement of the two.


page 2

page 4

page 6

page 7

page 8

page 9

page 12

page 13


NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction

We present a novel neural surface reconstruction method, called NeuS, fo...

Neural Sparse Voxel Fields

Photo-realistic free-viewpoint rendering of real-world scenes using clas...

Neural Volume Rendering: NeRF And Beyond

Besides the COVID-19 pandemic and political upheaval in the US, 2020 was...

Fast Neural Representations for Direct Volume Rendering

Despite the potential of neural scene representations to effectively com...

DDNeRF: Depth Distribution Neural Radiance Fields

In recent years, the field of implicit neural representation has progres...

A Learned Radiance-Field Representation for Complex Luminaires

We propose an efficient method for rendering complex luminaires using a ...

InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering

We present an information-theoretic regularization technique for few-sho...