Towards unified depth and semantic prediction from a single image

By Peng Wang, Xiaohui Shen, Zhe L. Lin, Scott D. Cohen, Brian L. Price, Alan L. Yuille. 2015

459 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

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (2016, methodology): “of segments [29], [30], [31], [32], [33], we use the fully connected pairwise CRF proposed by [22] for its efficient computation, and ability to capture fine edge details while also catering for long range dependencies.”
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs (2014, methodology): “, 2011) and/or high-order dependencies of segments (Delong et al., 2012; Gonfaus et al., 2010; Kohli et al., 2009; Chen et al., 2013; Wang et al., 2015), we use the fully connected pairwise CRF proposed by Krähenbühl & Koltun (2011) for its efficient computation, and ability to capture fine edge det”
Learning Like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images (2015, methodology): “For computer vision, deep Convolutional Neural Networks (CNN [31]) outperform previous methods by a large margin in the tasks of object classification [25, 44], detection [17, 40, 55] and segmentation [5, 52].”
Deeper Depth Prediction with Fully Convolutional Residual Networks (2016, methodology): “Another direction for improving the quality of the predicted depth maps has been the combined use of CNNs and graphical models [16, 19, 37].”
Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach (2018, methodology): “As shown in previous works [47], joint reasoning the depth and semantics improve the performance of both tasks.”
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.”
Semi-Supervised Deep Learning for Monocular Depth Map Prediction (2017, background): “Further lines of research in supervised training of depth map prediction use the idea of depth transfer from example images [13, 12, 21], or integrate depth map prediction with semantic segmentation [15, 19, 4, 26, 18].”
Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation (2018, methodology): “For example, a shared deep network is utilized to extract the common features for both tasks, and bifurcates from a high-level layer to perform the two tasks individually [16] [17] [22] [19] [21] [18].”
DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency (2018, background): “The availability of RGB-D datasets and deep learning leads to a line of work on single-view depth estimation [13,14,35,38,62,72].”
Towards Universal Object Detection by Domain Attention (2019, background): “Various multi-task networks [25, 62, 13, 28, 50, 63] have been proposed for joint solution of tasks such as object recognition, object detection, segmentation, edge detection, human pose, depth, action recognition, etc.”
Single-Image Depth Perception in the Wild (2016, background): “neural networks and RGB-D datasets [4, 5] has led to major advances [27, 6, 28, 8, 10, 14].”
Multi-scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation (2017, methodology): “Wang et al. [32] introduced a CNN for joint depth estimation and semantic segmentation.”
UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation (2019, unknown): “[58] 795 0.”
Deep Ordinal Regression Network for Monocular Depth Estimation (2018, methodology): “Rather than solely relying on deep networks, some methods incorporate conditional random ﬁelds to further improve the quality of estimated depth maps [57, 40].”
Synthetic Data for Deep Learning (2019, background): “They note that depth estimation and segmentation are related tasks that are increasingly learned together with multitask learning architectures [315, 446, 662] and then propose to use this idea to improve synthetic-to-real domain adaptation.”
CNN-SLAM: Real-Time Dense Monocular SLAM with Learned Depth Prediction (2017, methodology): “Recently developed deep convolutional architectures significantly outperformed previous methods in terms of depth estimation accuracy [16, 2, 3, 29, 19, 17].”
Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation (2019, methodology): “More recent works improved the performance of deep models by exploiting probabilistic graphical models implemented as neural networks [25, 36, 39, 38].”