Git Product home page Git Product logo

sga21_roofoptimization's Introduction

Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis

This is an example code for the paper "Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis", by Jing Ren, Biao Zhang, Bojian Wu, Jianqiang Huang, Lubin Fan, Maks Ovsjanikov, and Peter Wonka.

In this project, we propose a novel and flexible roof modeling approach that can be used for constructing planar 3D polygon roof meshes. Our method uses a graph structure to encode roof topology and enforces the roof validity by optimizing a simple planarity metric we propose. We showcase two applications: (1) an interactive roof editing framework that can be used for roof design or roof reconstruction from aerial images. (2) a generative model to synthesize new roof meshes from scratch.

You can find more details at: [paper] | [suppl. video] | [slides] | [presentation video]

Main Components

  • UIs for Image Annotation: We provide two web-based UIs, which can be used for specifying roof topology in the uploaded images/drawings.

  • Roof Optimization: From the input (or automatically generated) roof graph, we optimize for a valid 3D embedding of the roof such that each 3D roof face is planar. In this step we can also incorporate different regularizers or aesthetic constraints into the optimization formulation.

  • Roof Dataset: We created a building-image paired dataset that contains more than 3K samples using our roof modeling tools.

  • Application 01 - Roof Interactive Editing: Our optimization-based roof modeling formulation is compatible with different edits, including moving edges/vertices, snapping an edge, merging faces etc.

  • Application 02 - Roof Synthesis from Scratch: We also propose a generative model for roof synthesis from scratch.

Acknowledgement

  • The authors thank the anonymous reviewers for their valuable comments.
  • Parts of this work were supported by the KAUST OSR Award No. CRG-2017-3426, the ERC Starting Grant No. 758800 (EXPROTEA), the ANR AI Chair AIGRETTE, and Alibaba Innovative Research (AIR) Program.
  • We would like to thank Guangfan Pan and Jiacheng Ren for helping modeling roofs in 3ds Max and SketchUp, Jialin Zhu for helping designing the web-based roof annotation UIs, Jianhua Guo and Tom Kelly for helping with the comparison to the weighted straight skeleton. We thank Muxingzi Li for helping editing the supplementary video. We also thank Chuyi Qiu, Tianyu He, and Ran Yi for their valuable suggestions and comments.

Comments

sga21_roofoptimization's People

Contributors

llorz avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.