Laplacian Pyramid Neural Network for Dense Continuous-Value Regression for Complex Scenes
- 8 December 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 32 (11) , 5034-5046
Abstract
Many computer vision tasks, such as monocular depth estimation and height estimation from a satellite orthophoto, have a common underlying goal, which is regression of dense continuous values for the pixels given a single image. We define them as dense continuous-value regression (DCR) tasks. Recent approaches based on deep convolutional neural networks significantly improve the performance of DCR tasks, particularly on pixelwise regression accuracy. However, it still remains challenging to simultaneously preserve the global structure and fine object details in complex scenes. In this article, we take advantage of the efficiency of Laplacian pyramid on representing multiscale contents to reconstruct high-quality signals for complex scenes. We design a Laplacian pyramid neural network (LAPNet), which consists of a Laplacian pyramid decoder (LPD) for signal reconstruction and an adaptive dense feature fusion (ADFF) module to fuse features from the input image. More specifically, we build an LPD to effectively express both global and local scene structures. In our LPD, the upper and lower levels, respectively, represent scene layouts and shape details. We introduce a residual refinement module to progressively complement high-frequency details for signal prediction at each level. To recover the signals at each individual level in the pyramid, an ADFF module is proposed to adaptively fuse multiscale image features for accurate prediction. We conduct comprehensive experiments to evaluate a number of variants of our model on three important DCR tasks, i.e., monocular depth estimation, single-image height estimation, and density map estimation for crowd counting. Experiments demonstrate that our method achieves new state-of-the-art performance in both qualitative and quantitative evaluation on the NYU-D V2 and KITTI for monocular depth estimation, the challenging Urban Semantic 3D (US3D) for satellite height estimation, and four challenging benchmarks for crowd counting. These results demonstrate that the proposed LAPNet is a universal and effective architecture for DCR problems.Keywords
Funding Information
- National Key Research and Development Plan of China (2017YFB1002202)
- National Natural Science Foundation of China (61632006, U19B2038, 61620106009)
- Fundamental Research Funds for the Central Universities (WK3490000003)
This publication has 55 references indexed in Scilit:
- Building height estimation using Google EarthEnergy and Buildings, 2016
- Deep Neural Network for Structural Prediction and Lane Detection in Traffic SceneIEEE Transactions on Neural Networks and Learning Systems, 2016
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural FieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture2015
- Fully convolutional networks for semantic segmentation2015
- A new calculation method for shape coefficient of residential building using Google EarthEnergy and Buildings, 2014
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Multi-source Multi-scale Counting in Extremely Dense Crowd Images2013
- Using shadows in high-resolution imagery to determine building heightRemote Sensing Letters, 2011
- The Laplacian Pyramid as a Compact Image CodeIEEE Transactions on Communications, 1983