Convolutional Neural Pyramid for Image Processing
arXiv:1704.02071
Abstract
We propose a principled convolutional neural pyramid (CNP) framework for general low-level vision and image processing tasks. It is based on the essential finding that many applications require large receptive fields for structure understanding. But corresponding neural networks for regression either stack many layers or apply large kernels to achieve it, which is computationally very costly. Our pyramid structure can greatly enlarge the field while not sacrificing computation efficiency. Extra benefit includes adaptive network depth and progressive upsampling for quasi-realtime testing on VGA-size input. Our method profits a broad set of applications, such as depth/RGB image restoration, completion, noise/artifact removal, edge refinement, image filtering, image enhancement and colorization.
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Deep Residual Learning for Image Recognition
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Multi-Scale Context Aggregation by Dilated Convolutions
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
- Deeply-Recursive Convolutional Network for Image Super-Resolution
- On Vectorization of Deep Convolutional Neural Networks for Vision Tasks