Deep learning for monocular depth estimation: A review

Ming, Yue; Meng, Xuyang; Fan, Chunxiao; Yu, Hui

doi:10.1016/j.neucom.2020.12.089

Cited by 267 publications

(103 citation statements)

References 193 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The authors provide several results comparing DF-SLAM to ORB-SLAM2; for most sequences, the proposed algorithm obtained a better performance. Recently, it is possible to find, in the literature, several overviews [119][120][121] that address deep learning-based algorithms applied to depth estimation and the main concepts of SLAM's direction. More methods that use deep learning techniques are discussed in Section 4.3 as a solution to dynamic SLAM algorithms.…”

Section: Deep Learning-based Algorithmsmentioning

confidence: 99%

A Comprehensive Survey of Visual SLAM Algorithms

et al. 2022

View full text Add to dashboard Cite

Simultaneous localization and mapping (SLAM) techniques are widely researched, since they allow the simultaneous creation of a map and the sensors’ pose estimation in an unknown environment. Visual-based SLAM techniques play a significant role in this field, as they are based on a low-cost and small sensor system, which guarantees those advantages compared to other sensor-based SLAM techniques. The literature presents different approaches and methods to implement visual-based SLAM systems. Among this variety of publications, a beginner in this domain may find problems with identifying and analyzing the main algorithms and selecting the most appropriate one according to his or her project constraints. Therefore, we present the three main visual-based SLAM approaches (visual-only, visual-inertial, and RGB-D SLAM), providing a review of the main algorithms of each approach through diagrams and flowcharts, and highlighting the main advantages and disadvantages of each technique. Furthermore, we propose six criteria that ease the SLAM algorithm’s analysis and consider both the software and hardware levels. In addition, we present some major issues and future directions on visual-SLAM field, and provide a general overview of some of the existing benchmark datasets. This work aims to be the first step for those initiating a SLAM project to have a good perspective of SLAM techniques’ main elements and characteristics.

show abstract

Section: Deep Learning-based Algorithmsmentioning

confidence: 99%

A Comprehensive Survey of Visual SLAM Algorithms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…When the distance map is used as T in our FxSR, the foreground region is super-resolved in a perception-oriented way (with emphasized texture), and the background region in distortionoriented (somewhat blurry). Depth information obtained by some equipment such as Kinect [70] and Time-of-Flight (ToF) camera [71], [72], or depth estimation algorithms [73] can be used. It is also possible for users to directly generate a depth map from an input image using image editing S/W, as shown in Figure 18.…”

Section: Per-pixel Style Controlmentioning

confidence: 99%

Flexible Style Image Super-Resolution Using Conditional Objective

2022

View full text Add to dashboard Cite

Recent studies have significantly enhanced the performance of single-image super-resolution (SR) using convolutional neural networks (CNNs). While there can be many high-resolution (HR) solutions for a given input, most existing CNN-based methods do not explore alternative solutions during the inference. A typical approach to obtaining alternative SR results is to train multiple SR models with different loss weightings and exploit the combination of these models. Instead of using multiple models, we present a more efficient method to train a single adjustable SR model on various combinations of losses by taking advantage of multi-task learning. Specifically, we optimize an SR model with a conditional objective during training, where the objective is a weighted sum of multiple perceptual losses at different feature levels. The weights vary according to given conditions, and the set of weights is defined as a style controller. Also, we present an architecture appropriate for this training scheme, which is the Residual-in-Residual Dense Block equipped with spatial feature transformation layers. At the inference phase, our trained model can generate locally different outputs conditioned on the style control map. Extensive experiments show that the proposed SR model produces various desirable reconstructions without artifacts and yields comparable quantitative performance to state-of-the-art SR methods. Code and trained models are available at https://github.com/seungho-snu/FxSR.

show abstract

“…In recent years, the technologies of machine learning and deep learning has achieved impressive performance in various fields such as computer vision and pattern recognition [26,28,30,31,36,38,42,43]. One of the deep learning methods, Generative Adversarial Networks (GANs) [27] designed according to the game theory have attracted increasing attention recently.…”

Section: Related Workmentioning

confidence: 99%

Local and Global Perception Generative Adversarial Network for Facial Expression Synthesis

Xia

Zheng

Wang

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

Facial expression synthesis has gained increasing attention with the development of Generative Adversarial Networks (GANs). However, it is still very challenging to generate high-quality facial expressions since the overlapping and blur commonly appear in the generated facial images especially in the regions with rich facial features such as eye and mouth. Generally, existing methods mainly consider the face as a whole in facial expression synthesis without paying specific attention to the characteristics of facial expressions. In fact, according to the physiological and psychological research, the differences of facial expressions often appear in crucial regions such as eye and mouth. Motivated by this observation, a novel end-toend facial expression synthesis method called Local and Global Perception Generative Adversarial Network (LGP-GAN) with a two-stage cascaded structure is proposed in this paper which is designed to extract and synthesize the details of the crucial facial regions. LGP-GAN can combine the generated results from the global network and local network into the corresponding facial expressions. In Stage I, LGP-GAN utilizes local networks to capture the local texture details of the crucial facial regions and generate local facial regions, which fully explores crucial facial region domain information in facial expressions. And then LGP-GAN uses a global network to learn the whole facial information in Stage II to generate the generate final facial expressions building upon local generated results from Stage I. We conduct qualitative and quantitative experiments on the commonly used public database to verify the effectiveness of the proposed method. Experimental results show the superiority of the proposed method over the state-of-the-art methods.

show abstract

Deep learning for monocular depth estimation: A review

Cited by 267 publications

References 193 publications

A Comprehensive Survey of Visual SLAM Algorithms

A Comprehensive Survey of Visual SLAM Algorithms

Flexible Style Image Super-Resolution Using Conditional Objective

Local and Global Perception Generative Adversarial Network for Facial Expression Synthesis

Contact Info

Product

Resources

About