Tree-Structured Shading Decomposition

Chen Geng, Hong-Xing Yu, Sharon Zhang, Maneesh Agrawala, Jiajun Wu; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 488-498

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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Geng_2023_ICCV, author = {Geng, Chen and Yu, Hong-Xing and Zhang, Sharon and Agrawala, Maneesh and Wu, Jiajun}, title = {Tree-Structured Shading Decomposition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {488-498} }