Differentiable Neural Implicits

Differential Geometry in Neural Implicits

lvelho — Sun, 30 Jan 2022 18:30:09 +0000

We introduce a neural implicit framework that bridges discrete differential geometry of triangle meshes and continuous differential geometry of neural implicit surfaces. It exploits the differentiable properties of neural networks and the discrete geometry of triangle meshes to approximate them as the zero-level sets of neural implicit functions.

Neural Implicit Surfaces in Higher Dimension

lvelho — Sun, 30 Jan 2022 18:24:56 +0000

This work investigates the use of neural networks admitting high-order derivatives for modeling dynamic variations of smooth implicit surfaces. For this purpose, it extends the representation of differentiable neural implicit surfaces to higher dimensions, which opens up mechanisms that allow to exploit geometric transformations in many settings, from animation and surface evolution to shape morphing and design galleries.

MIP-plicits: Level of Detail Factorization of Neural Implicits Sphere Tracing

lvelho — Sun, 30 Jan 2022 17:36:12 +0000

We introduce MIP-plicits, a novel approach for rendering 3D and 4D Neural Implicits that divide the problem into macro and meso components.
We also introduce Neural Implicit Normal Mapping, which is a core component of the problem factorization