Inspired by the recent advance of image-based object reconstruction using deep learning, we present an active reconstruction model using a guided view planner. We aim to reconstruct a 3D model using images observed from a planned sequence of informative and discriminative views. But where are such informative and discriminative views around an object? To address this we propose a unified model for view planning and object reconstruction, which is utilized to learn a guided information acquisition model and to aggregate information from a sequence of images for reconstruction. Experiments show that our model (1) increases our reconstruction accuracy with an increasing number of views (2) and generally predicts a more informative sequence of views for object reconstruction compared to other alternative methods.
@article{arxiv.1805.03081,
title = {Active Object Reconstruction Using a Guided View Planner},
author = {Xin Yang and Yuanbo Wang and Yaru Wang and Baocai Yin and Qiang Zhang and Xiaopeng Wei and Hongbo Fu},
journal= {arXiv preprint arXiv:1805.03081},
year = {2018}
}