资源论文Adopting an Unconstrained Ray Model in Light-field Cameras for 3D Shape Reconstruction

Adopting an Unconstrained Ray Model in Light-field Cameras for 3D Shape Reconstruction

2019-12-25 | |  52 |   47 |   0

Abstract

Given the raising interest in light-field technology andthe increasing availability of professional devices, a feasi-ble and accurate calibration method is paramount to un-leash practical applications. In this paper we propose toembrace a fully non-parametric model for the imaging andwe show that it can be properly calibrated with little effortusing a dense active target. This process produces a denseset of independent rays that cannot be directly used to pro-duce a conventional image. However, they are an ideal toolfor 3D reconstruction tasks, since they are highly redundant, very accurate and they cover a wide range of different baselines. The feasibility and convenience of the process and the accuracy of the obtained calibration are compre-hensively evaluated through several experiments.

上一篇:The Stitched Puppet: A Graphical Model of 3D Human Shape and Pose

下一篇:Recurrent Convolutional Neural Network for Object Recognition

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...