Learning to Infer 3D Shape Programs with Differentiable Renderer

TL;DR

This paper introduces a differentiable executor for 3D shape programs that improves interpretability, control, and sample efficiency, enabling better reasoning about shape regularities without requiring training data.

Contribution

It presents a more faithful and controllable differentiable executor for 3D shape programs, enhancing interpretability and learning efficiency over previous methods.

Findings

The executor is more faithful in interpreting shape programs.

It requires no training data, improving sample efficiency.

Preliminary experiments show advantages in adaptation and reasoning.

Abstract

Given everyday artifacts, such as tables and chairs, humans recognize high-level regularities within them, such as the symmetries of a table, the repetition of its legs, while possessing low-level priors of their geometries, e.g., surfaces are smooth and edges are sharp. This kind of knowledge constitutes an important part of human perceptual understanding and reasoning. Representations of and how to reason in such knowledge, and the acquisition thereof, are still open questions in artificial intelligence (AI) and cognitive science. Building on the previous proposal of the \emph{3D shape programs} representation alone with the accompanying neural generator and executor from \citet{tian2019learning}, we propose an analytical yet differentiable executor that is more faithful and controllable in interpreting shape programs (particularly in extrapolation) and more sample efficient (requires no training). These facilitate the generator's learning when ground truth programs are not available, and should be especially useful when new shape-program components are enrolled either by human designers or -- in the context of library learning -- algorithms themselves. Preliminary experiments on using it for adaptation illustrate the aforesaid advantages of the proposed module, encouraging similar methods being explored in building machines that learn to reason with the kind of knowledge described above, and even learn this knowledge itself.