A Two-Streamed Network for Estimating Fine-Scaled Depth Maps From Single RGB Images

Jun Li, Reinhard Klein, Angela Yao; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 3372-3380

Abstract


Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem. State-of-the-art deep learning methods can now estimate accurate 2D depth maps, but when the maps are projected into 3D, they lack local detail and are often highly distorted. We propose a fast-to-train two-streamed CNN that predicts depth and depth gradients, which are then fused together into an accurate and detailed depth map. We also define a novel set loss over multiple images; by regularizing the estimation between a common set of images, the network is less prone to over-fitting and achieves better accuracy than competing methods. Experiments on the NYU Depth v2 dataset shows that our depth predictions are competitive with state-of-the-art and lead to faithful 3D projections.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Li_2017_ICCV,
author = {Li, Jun and Klein, Reinhard and Yao, Angela},
title = {A Two-Streamed Network for Estimating Fine-Scaled Depth Maps From Single RGB Images},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}