Constructing Printable Surfaces with View-Dependent Appearance

TL;DR

This paper introduces a novel method for designing and fabricating surfaces with view-dependent appearance by optimizing a colored heightfield mesh using a differentiable rendering algorithm and machine learning, enabling realistic 3D printed effects.

Contribution

The paper presents a new differentiable rendering algorithm for colored heightfields and an ML-based optimization process for creating view-dependent surfaces for fabrication.

Findings

Successful synthesis of view-dependent surfaces

Effective 3D printing of fabricated surfaces

Demonstrated both synthetic and real-world results

Abstract

We present a method for the digital fabrication of surfaces whose appearance varies based on viewing direction. The surfaces are constructed from a mesh of bars arranged in a self-occluding colored heightfield that creates the desired view-dependent effects. At the heart of our method is a novel and simple differentiable rendering algorithm specifically designed to render colored 3D heightfields and enable efficient calculation of the gradient of appearance with respect to heights and colors. This algorithm forms the basis of a coarse-to-fine ML-based optimization process that adjusts the heights and colors of the strips to minimize the loss between the desired and real surface appearance from each viewpoint, deriving meshes that can then be fabricated using a 3D printer. Using our method, we demonstrate both synthetic and real-world fabricated results with view-dependent appearance.