@inproceedings{weder2021neuralfusion,
author = {Weder, Silvan and Schönberger, Johannes L. and Pollefeys, Marc and Oswald, Martin R.},
title = {NeuralFusion: Online Depth Fusion in Latent Space},
booktitle = {CVPR 2021},
year = {2021},
month = {June},
abstract = {We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. While previous fusion methods use an explicit scene representation like signed distance functions (SDFs), we propose a learned feature representation for the fusion. The key idea is a separation between the scene representation used for the fusion and the output scene representation, via an additional translator network. Our neural network architecture consists of two main parts: a depth and feature fusion sub-network, which is followed by a translator sub-network to produce the final surface representation (e.g. TSDF) for visualization or other tasks. Our approach is real-time capable, handles high noise levels, and is particularly able to deal with gross outliers common for photometric stereo-based depth maps. Experiments on real and synthetic data demonstrate improved results compared to the state of the art, especially in challenging scenarios with large amounts of noise and outliers.},
url = {http://approjects.co.za/?big=en-us/research/publication/neuralfusion-online-depth-fusion-in-latent-space/},
}