FADNet: A Fast and Accurate Network for Disparity Estimation

Wang, Qiang; Shi, Shaohuai; Zheng, Shizhen; Zhao, Kaixuan; Chu, Xiaowen

doi:10.1109/icra40945.2020.9197031

Cited by 64 publications

(43 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we can see, compared with other 2D stereo networks (AANet [ 18 ], FADNet [ 20 ], DispNetC [ 22 ], etc. ), our method achieves a large improvement on performance, while the running time only increases a little.…”

Section: Methodsmentioning

confidence: 94%

“…In terms of different matching cost computation methods, current neural network-based stereo methods can be mainly divided into the following: 2D networks [ 18 , 19 , 20 , 21 , 22 , 23 ] with cost volumes generated by traditional methods or the correlation layer. 3D networks [ 24 , 25 , 26 , 27 ] with cost volumes generated by concatenation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Joint 2D-3D Complementary Network for Stereo Matching

Jia¹,

Chen²,

Liang³

et al. 2021

Sensors

View full text Add to dashboard Cite

Stereo matching is an important research field of computer vision. Due to the dimension of cost aggregation, current neural network-based stereo methods are difficult to trade-off speed and accuracy. To this end, we integrate fast 2D stereo methods with accurate 3D networks to improve performance and reduce running time. We leverage a 2D encoder-decoder network to generate a rough disparity map and construct a disparity range to guide the 3D aggregation network, which can significantly improve the accuracy and reduce the computational cost. We use a stacked hourglass structure to refine the disparity from coarse to fine. We evaluated our method on three public datasets. According to the KITTI official website results, Our network can generate an accurate result in 80 ms on a modern GPU. Compared to other 2D stereo networks (AANet, DeepPruner, FADNet, etc.), our network has a big improvement in accuracy. Meanwhile, it is significantly faster than other 3D stereo networks (5× than PSMNet, 7.5× than CSN and 22.5× than GANet, etc.), demonstrating the effectiveness of our method.

show abstract

Section: Methodsmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

A Joint 2D-3D Complementary Network for Stereo Matching

Jia¹,

Chen²,

Liang³

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…We also enhanced the MRF unit, as illustrated in Figure 3(d). Deep residual networks obtain rich feature information from multisize inputs [36]. Residual blocks, originally derived for image classification tasks,are extensively used to learn robust features and train deeper networks.…”

Section: Model Design and Implementationmentioning

confidence: 99%

Joint Generative Image Deblurring Aided by Edge Attention Prior and Dynamic Kernel Selection

Zhang

Chen

Yin

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Image deblurring is a classic and important problem in industrial fields, such as aviation photo restoration, object recognition in robotics, and autonomous vehicles. Blurry images in real-world scenarios consist of mixed blurring types, such as a natural motion blurring owing to shaking of the camera. Fast deblurring does not deblur the entire image because it is not the best option. Considering the computational costs, it is also better to have an alternative kernel to deblur different objects at a high-semantic level. To achieve better image restoration quality, it is also beneficial to combine the blurring category location and important structural information in terms of specific artifacts and degree of blurring. The goal of blind image deblurring is to restore sharpness from the unknown blurring kernel of an image. Recent deblurring methods tend to reconstruct prior knowledge, neglecting the influence of blur estimation and visual fidelity on image details and structure. Generative adversarial networks(GANs) have recently been attracting considerable attention from both academia and industry because GAN can perfectly generate new data with the same statistics as the training set. Therefore, this study proposes a generative neural architecture and an edge attention algorithm developed to restore vivid multimedia patches. Joint edge generation and image restoration techniques are designed to solve the low-level multimedia retrieval. This multipath refinement fusion network (MRFNet) can not only perform deblurring of images directly but also individual the frames separately from videos. Ablation experiments validate that our generative adversarial network MRFNet performs better in joint training than in multimodel. Compared to other GAN methods, our two-phase method exhibited state-of-the-art performance in terms of speed and accuracy as well as has a significant visual improvement.

show abstract

“…Building cost volume by simple feature correlation instead of concatenation or subtraction, can be a common way to decrease computation complexity and achieve fast speed, such as DispNet [7], FADNet [8] and AANet [9]. The traditional 1D correlation along disparity line generates 3D cost volume and reduce complexity, but it loses information on account of its straightforward approximation to the volume.…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Context Guided Aggregation Network for Stereo Matching

Peng

Xie

Huang

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Nowadays, CNN-based stereo matching methods achieved remarkable performance, and how to efficiently exploit contextual information in cost aggregation stage is the key to improve performance. In this paper, we propose a simple yet efficient network named Hierarchical Context Guided Aggregation Network (HCGANet). Specifically, a novel cost aggregation module is developed to replace widely used 3D convolutions. Firstly, we construct pyramid cost volumes which carry multi-level distinctive and discriminative representation. Additionally, an intra-level aggregation module is presented for single-level regularization and contextual information learning. Moreover, we develop an inter-level aggregation module to hierarchically regularize cost volumes via the guidance from coarser scales. The proposed aggregation module is lightweight and complementary, further improving the robustness and performance of disparity estimation. Extensive experiments demonstrate that the proposed method achieves superior results for both efficiency and accuracy on Scene-Flow and KITTI benchmarks.

show abstract

FADNet: A Fast and Accurate Network for Disparity Estimation

Cited by 64 publications

References 16 publications

A Joint 2D-3D Complementary Network for Stereo Matching

A Joint 2D-3D Complementary Network for Stereo Matching

Joint Generative Image Deblurring Aided by Edge Attention Prior and Dynamic Kernel Selection

Hierarchical Context Guided Aggregation Network for Stereo Matching

Contact Info

Product

Resources

About