FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks

10/06/2021
by   Qiang Wang, et al.
9

Deep neural networks (DNNs) have achieved great success in the area of computer vision. The disparity estimation problem tends to be addressed by DNNs which achieve much better prediction accuracy than traditional hand-crafted feature-based methods. However, the existing DNNs hardly serve both efficient computation and rich expression capability, which makes them difficult for deployment in real-time and high-quality applications, especially on mobile devices. To this end, we propose an efficient, accurate, and configurable deep network for disparity estimation named FADNet++. Leveraging several liberal network design and training techniques, FADNet++ can boost its accuracy with a fast model inference speed for real-time applications. Besides, it enables users to easily configure different sizes of models for balancing accuracy and inference efficiency. We conduct extensive experiments to demonstrate the effectiveness of FADNet++ on both synthetic and realistic datasets among six GPU devices varying from server to mobile platforms. Experimental results show that FADNet++ and its variants achieve state-of-the-art prediction accuracy, and run at a significant order of magnitude faster speed than existing 3D models. With the constraint of running at above 15 frames per second (FPS) on a mobile GPU, FADNet++ achieves a new state-of-the-art result for the SceneFlow dataset.

READ FULL TEXT

page 1

page 2

page 4

page 9

page 10

page 11

page 13

research
03/24/2020

FADNet: A Fast and Accurate Network for Disparity Estimation

Deep neural networks (DNNs) have achieved great success in the area of c...
research
11/18/2020

ADCPNet: Adaptive Disparity Candidates Prediction Network for Efficient Real-Time Stereo Matching

Efficient real-time disparity estimation is critical for the application...
research
12/05/2019

PhoneBit: Efficient GPU-Accelerated Binary Neural Network Inference Engine for Mobile Phones

Over the last years, a great success of deep neural networks (DNNs) has ...
research
10/13/2016

GPU-accelerated real-time stixel computation

The Stixel World is a medium-level, compact representation of road scene...
research
11/08/2017

Efficient Destination Prediction Based on Route Choices with Transition Matrix Optimization

Destination prediction is an essential task in a variety of mobile appli...
research
10/30/2018

R^3SGM: Real-time Raster-Respecting Semi-Global Matching for Power-Constrained Systems

Stereo depth estimation is used for many computer vision applications. T...
research
06/10/2021

Context-Free TextSpotter for Real-Time and Mobile End-to-End Text Detection and Recognition

In the deployment of scene-text spotting systems on mobile platforms, li...

Please sign up or login with your details

Forgot password? Click here to reset