Portrait Quality Assessment using Multi-Scale CNN

Pollution Portrait: The Fourth National-Scale Air Toxics Assessment

Large-Scale 3D Scene Classification With Multi-View Volumetric CNN

We introduce a method to classify imagery using a convolutional neural network (CNN) on multi-view image projections. The power of our method comes from using projections of multiple images at multiple depth planes near the reconstructed surface. This enables classification of categories whose salient aspect is appearance change under different viewpoints, such as water, trees, and other materi...

Multi-scale Structural Similarity for Image Quality Assessment

The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a multi-scale structural similarity method, which supplies more flexibility than previous ...

A Multi-scale CNN for Affordance Segmentation in RGB Images

Given a single RGB image our goal is to label every pixel with an affordance type. By affordance, we mean an object’s capability to readily support a certain human action, without requiring precursor actions. We focus on segmenting the following five affordance types in indoor scenes: ‘walkable’, ‘sittable’, ‘lyable’, ‘reachable’, and ‘movable’. Our approach uses a deep architecture, consisting...

Image Quality Assessment by Comparing CNN Features Between Images -

Finding an objective image quality metric that matches the subjective quality has always been a challenging task. We propose a new full reference image quality metric based on features extracted from Convolutional Neural Networks (CNNs). Using a pre-trained AlexNet model, we extract feature maps of the test and reference images at multiple layers, and compare their feature similarity at each la...