Neural Implicit Surfaces in Higher Dimension
share
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. The problem is modeled by a k-parameter family of surfaces S_c, specified as a neural network function f : ℝ^3 ×ℝ^k →ℝ, where S_c is the zero-level set of the implicit function f(·, c) : ℝ^3 →ℝ, with c ∈ℝ^k, with variations induced by the control variable c. In that context, restricted to each coordinate of ℝ^k, the underlying representation is a neural homotopy which is the solution of a general partial differential equation.
READ FULL TEXT