Tree-Structured Shading Decomposition

TL;DR

This paper introduces a novel shade tree representation for object shading inference from a single image, enabling intuitive editing and applications like relighting, by combining a hybrid inference approach for structure and parameters.

Contribution

It proposes a new shade tree model for shading decomposition that is interpretable and editable, along with a hybrid inference method for structure and parameter estimation.

Findings

Effective on synthetic and real images

Enables intuitive shading editing

Supports downstream applications like relighting

Abstract

We study inferring a tree-structured representation from a single image for object shading. Prior work typically uses the parametric or measured representation to model shading, which is neither interpretable nor easily editable. We propose using the shade tree representation, which combines basic shading nodes and compositing methods to factorize object surface shading. The shade tree representation enables novice users who are unfamiliar with the physical shading process to edit object shading in an efficient and intuitive manner. A main challenge in inferring the shade tree is that the inference problem involves both the discrete tree structure and the continuous parameters of the tree nodes. We propose a hybrid approach to address this issue. We introduce an auto-regressive inference model to generate a rough estimation of the tree structure and node parameters, and then we fine-tune the inferred shade tree through an optimization algorithm. We show experiments on synthetic images, captured reflectance, real images, and non-realistic vector drawings, allowing downstream applications such as material editing, vectorized shading, and relighting. Project website: https://chen-geng.com/inv-shade-trees