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. 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 is in contrast to previous work modeling the geometry as a function of the volume density. We achieve that by modeling the volume density as a function of the geometry. The goal of this paper is to improve geometry representation and reconstruction in neural volume rendering. Furthermore, the geometry itself was extracted using an arbitrary level set of the density function leading to a noisy, often low fidelity reconstruction. So far, the geometry learned by neural volume rendering techniques was modeled using a generic density function. 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.
0 Comments
Leave a Reply. |