Convolutional Neural Network (CNN) has achieved particularly good results on depth estimation from a single image. However, certain disadvantages exist including: (1) Traditional CNNs adopt pooling layers to increase the receptive field, but it will lower the resolution and cause the information loss. ( 2) Almost all frameworks of CNN proposed for depth estimation apply the fully connected layers to obtain global information and they will introduce too many parameters which often result in out-of-memory problems. In this paper, we present a new module named dilated fully convolutional neural network to tackle these disadvantages. On one hand, the developed method takes advantages of dilated convolutions that can support the exponential expansion of the receptive field without loss of resolution; On the other hand, our module replaces the fully connected layers with the fully convolutional layers, which can significantly reduce the number of parameters to make our module more universal. By experiments, we show that the presented module achieves state-of-the-art results on NYU Depth V2 datasets.

No abstract

Depth prediction plays a key role in understanding a 3D scene. Several techniques have been developed throughout the years, among which Convolutional Neural Network has recently achieved state-of-the-art performance on estimating depth from a single image. However, traditional CNNs suffer from the lower resolution and information loss caused by the pooling layers. And oversized parameters generated from fully connected layers often lead to a exploded memory usage problem. In this paper, we present an advanced Dilated Fully Convolutional Neural Network to address the deficiencies. Taking advantages of the exponential expansion of the receptive field in dilated convolutions, our model can minimize the loss of resolution. It also reduces the amount of parameters significantly by replacing the fully connected layers with the fully convolutional layers. We show experimentally on NYU Depth V2 datasets that the depth prediction obtained from our model is considerably closer to ground truth than that from traditional CNNs techniques.

No abstract

Haze removal is an extremely challenging task, and object detection in the hazy environment has recently gained much attention due to the popularity of autonomous driving and traffic surveillance. In this work, the authors propose a multiple linear regression haze removal model based on a widely adopted dehazing algorithm named Dark Channel Prior. Training this model with a synthetic hazy dataset, the proposed model can reduce the unanticipated deviations generated from the rough estimations of transmission map and atmospheric light in Dark Channel Prior. To increase object detection accuracy in the hazy environment, the authors further present an algorithm to build a synthetic hazy COCO training dataset by generating the artificial haze to the MS COCO training dataset. The experimental results demonstrate that the proposed model obtains higher image quality and shares more similarity with ground truth images than most conventional pixel-based dehazing algorithms and neural network based haze-removal models. The authors also evaluate the mean average precision of Mask R-CNN when training the network with synthetic hazy COCO training dataset and preprocessing test hazy dataset by removing the haze with the proposed dehazing model. It turns out that both approaches can increase the object detection accuracy significantly and outperform most existing object detection models over hazy images.