Discrete-Continuous Depth Estimation from a Single Image

By Miaomiao Liu, Mathieu Salzmann, Xuming He. 2014

380 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (2017, background): “ing both aleatoric and epistemic uncertainty gives a notable improvement in segmentation accuracy over state of the art baselines. Make3D rel rms log 10 Karsch et al. [33] 0.355 9.20 0.127 Liu et al. [34] 0.335 9.49 0.137 Li et al. [35] 0.278 7.19 0.092 Laina et al. [26] 0.176 4.46 0.072 This work: ”
Deep convolutional neural fields for depth estimation from a single image (2014, methodology): “Note that the C2 errors of [16] are reported with an ad-hoc post-processing step, which trains a classifier to label sky pixels and set the corresponding regions to the maximum depth.”
Unsupervised Learning of Depth and Ego-Motion from Video (2017, neutral): “[33] 0.”
Deeper Depth Prediction with Fully Convolutional Residual Networks (2016, methodology): “A second cluster of related work comprises non-parametric approaches for depth transfer [10, 13, 18, 20], which typically perform feature-based matching (e.”
Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image (2017, methodology): “Non-parametric approaches [9–12] were also exploited to estimate the depth of a query image by combining the depths of images with similar photometric content retrieved from a database.”
DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency (2018, neutral): “ highlighted as bold and underline. Error metric # Method Supervision Abs Rel Sq Rel RMSE log RMSE Train set mean - 0.876 12.98 12.27 0.307 Karsch et al. [29] depth 0.428 5.079 8.389 0.149 Liu et al. [39] depth 0.475 6.562 10.05 0.165 Laina et al. [34] depth 0.204 1.840 5.683 0.084 Li et al. [36] de”
GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation (2018, background): “There exist a large amount of methods on depth estimation [25, 19, 8, 7, 21, 31, 24, 16, 20, 34, 18] and surface normal estimation [7, 33, 3, 2, 18] from a single image.”
DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene From Sparse LiDAR Data and Single Color Image (2018, methodology): “Early methods mainly relied on the hand-crafted features and probabilistic graphical models [42, 21, 22, 24, 31].”
MegaDepth: Learning Single-View Depth Prediction from Internet Photos (2018, neutral): “[24] 9.”
Towards unified depth and semantic prediction from a single image (2015, methodology): “Data-driven approaches based on non-parametric transfer are another popular trend in both scene parsing [5] [32] [33] [35] and depth estimation [17] [24].”
Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs (2015, methodology): “Parametric approaches such as [9] and [11] make a planar model for each super-pixel, where the model parameters are inferred by exploiting different unary, pair-wise and high-order cues.”
Learning to Count with CNN Boosting (2016, methodology): “Therefore, we follow the commonly applied post-processing described in [38] that classifies sky pixels and sets their depth to 80m.”
Digging Into Self-Supervised Monocular Depth Estimation (2018, neutral): “149 Liu [38] D 0.”
Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation (2018, background): “…multiscale information (Eigen et al. [6], Eigen and Fergus [5], Li et al. [21]), with approaches which consider graphical models (Liu et al. [24], Liu et al. [22], Zhuo et al. [39], Wang et al. [31], Xu et al. [36]) and neural regression forests ([26]), and with meth-ods which explore the…”
Real-Time Monocular Depth Estimation Using Synthetic Data with Domain Adaptation via Image Style Transfer (2018, result): “[36, 50, 40] are specifically trained on Make3D.”
Multi-scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation (2017, methodology): “Depth estimation was treated as an inference problem in a discrete-continuous CRF in [21].”
Superpixels: An evaluation of the state-of-the-art (2016, background): “We found that UE tends to correlate strongly with ASA which can be explained by Equations (3) and (6), respectively.”