# A Data-driven Approach for Furniture and Indoor Scene Colorization

## TL;DR

This paper introduces a data-driven system that automatically colorizes 3D furniture and indoor scenes by learning from internet images, supporting example-based colorization and user-guided schemes, producing results comparable to interior designers.

## Contribution

It presents a novel image-guided mesh segmentation method and a hierarchical image-model database for realistic, user-controllable indoor scene colorization.

## Key findings

- System produces perceptually convincing results
- Supports colorization-by-example and user-guided schemes
- Comparable to interior designer results

## Abstract

We present a data-driven approach that colorizes 3D furniture models and indoor scenes by leveraging indoor images on the internet. Our approach is able to colorize the furniture automatically according to an example image. The core is to learn image-guided mesh segmentation to segment the model into different parts according to the image object. Given an indoor scene, the system supports colorization-by-example, and has the ability to recommend the colorization scheme that is consistent with a user-desired color theme. The latter is realized by formulating the problem as a Markov random field model that imposes user input as an additional constraint. We contribute to the community a hierarchically organized image-model database with correspondences between each image and the corresponding model at the part-level. Our experiments and a user study show that our system produces perceptually convincing results comparable to those generated by interior designers.