Deeplidar: Deep surface normal guided depth prediction for outdoor scene from sparse lidar data and single color image

J Qiu, Z Cui, Y Zhang, X Zhang, S Liu… - Proceedings of the …, 2019 - openaccess.thecvf.com
In this paper, we propose a deep learning architecture that produces accurate dense depth
for the outdoor scene from a single color image and a sparse depth. Inspired by the indoor …

Sparse-to-dense: Depth prediction from sparse depth samples and a single image

F Ma, S Karaman - 2018 IEEE international conference on …, 2018 - ieeexplore.ieee.org
We consider the problem of dense depth prediction from a sparse set of depth
measurements and a single RGB image. Since depth estimation from monocular images …

Deeper depth prediction with fully convolutional residual networks

I Laina, C Rupprecht, V Belagiannis… - … conference on 3D …, 2016 - ieeexplore.ieee.org
This paper addresses the problem of estimating the depth map of a scene given a single
RGB image. We propose a fully convolutional architecture, encompassing residual learning …

Semi-supervised deep learning for monocular depth map prediction

Y Kuznietsov, J Stuckler… - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
Supervised deep learning often suffers from the lack of sufficient training data. Specifically in
the context of monocular depth map prediction, it is barely possible to determine dense …

Fastdepth: Fast monocular depth estimation on embedded systems

D Wofk, F Ma, TJ Yang, S Karaman… - … Conference on Robotics …, 2019 - ieeexplore.ieee.org
Depth sensing is a critical function for robotic tasks such as localization, mapping and
obstacle detection. There has been a significant and growing interest in depth estimation …

Deepstereo: Learning to predict new views from the world's imagery

J Flynn, I Neulander, J Philbin… - Proceedings of the IEEE …, 2016 - cv-foundation.org
Deep networks have recently enjoyed enormous success when applied to recognition and
classification problems in computer vision [22, 32], but their use in graphics problems has …

Depth and surface normal estimation from monocular images using regression on deep features and hierarchical crfs

B Li, C Shen, Y Dai… - Proceedings of the …, 2015 - openaccess.thecvf.com
Predicting the depth (or surface normal) of a scene from single monocular color images is a
challenging task. This paper tackles this challenging and essentially under-determined …

Learning joint 2d-3d representations for depth completion

Y Chen, B Yang, M Liang… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
In this paper, we tackle the problem of depth completion from RGBD data. Towards this goal,
we design a simple yet effective neural network block that learns to extract joint 2D and 3D …

Discrete-continuous depth estimation from a single image

M Liu, M Salzmann, X He - … of the IEEE conference on computer …, 2014 - cv-foundation.org
In this paper, we tackle the problem of estimating the depth of a scene from a single image.
This is a challenging task, since a single image on its own does not provide any depth cue …

Single view stereo matching

Y Luo, J Ren, M Lin, J Pang, W Sun… - Proceedings of the …, 2018 - openaccess.thecvf.com
Previous monocular depth estimation methods take a single view and directly regress the
expected results. Though recent advances are made by applying geometrically inspired loss …