Giter Club home page Giter Club logo

ml-live-pose's Introduction

LivePose

This repository accompanies the research paper, LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses and contains the data described in the paper.

LivePose data figure

Paper

LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses

Upon using these data or source code, please cite:

@inproceedings{stier2023livepose,
      title={LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses}, 
      author={Noah Stier and Baptiste Angles and Liang Yang and Yajie Yan and Alex Colburn and Ming Chuang},
      booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
      year={2023},
}

The dataset

The LivePose dataset consists of dynamic pose-tracking data produced by running the BundleFusion SLAM system on the ScanNet dataset of RGB-D scans. For each ScanNet scene, LivePose contains the BundleFusion pose output stored as an initial pose estimate plus subsequent pose updates for each camera view. The pose updates are grouped into update bundles occurring at approximately 3Hz, where each bundle can contain pose updates for any number of past views.

The dataset contains one text file for each of the 1,613 ScanNet scans. Each line of each file contains a pose estimate formatted as 14 space-separated numbers where the first is the integer index of the frame at which this pose estimate was issued, the second is the integer index of the frame that this pose estimate refers to, and the remaining 12 are the coefficients of the 3x4 camera-to-world transformation matrix in row-major order.

Download

The dataset can be found at: https://docs-assets.developer.apple.com/ml-research/datasets/live-pose/LivePoseDataset.zip

License

The LivePose dataset is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-sa/4.0/.

The third party ScanNet data is made available by ScanNet at http://www.scan-net.org/ and is subject to the ScanNet Terms of Use and ScanNet license.

ml-live-pose's People

Contributors

baptisteangles avatar noahstier avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.