Deep Boosting for Image Denoising

ECCV 2018  ·  Chang Chen, Zhiwei Xiong, Xinmei Tian, Feng Wu ·

Boosting is a classic algorithm which has been successfully applied to diverse computer vision tasks. In the scenario of image denoising, however, the existing boosting algorithms are surpassed by the emerging learning-based models. In this paper, we propose a novel deep boosting framework (DBF) for denoising, which integrates several convolutional networks in a feed-forward fashion. Along with the integrated networks, however, the depth of the boosting framework is substantially increased, which brings difficulty to training. To solve this problem, we introduce the concept of dense connection that overcomes the vanishing of gradients during training. Furthermore, we propose a path-widening fusion scheme cooperated with the dilated convolution to derive a lightweight yet efficient convolutional network as the boosting unit, named Dilated Dense Fusion Network (DDFN). Comprehensive experiments demonstrate that our DBF outperforms existing methods on widely used benchmarks, in terms of different denoising tasks.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Salt-And-Pepper Noise Removal Kodak24 Noise Level 30% DeepBoosting PSNR 21.69 # 3
Salt-And-Pepper Noise Removal Kodak24 Noise Level 50% DeepBossting PSNR 19.50 # 3
Salt-And-Pepper Noise Removal Kodak24 Noise Level 70% DeepBoosting PSNR 15.74 # 3

Methods