Search
Results
-
Unsupervised Deep Single‐Image Intrinsic Decomposition using Illumination‐Varying Image Sequences
(2018)Computer Graphics ForumMachine learning based Single Image Intrinsic Decomposition (SIID) methods decompose a captured scene into its albedo and shading images by using the knowledge of a large set of known and realistic ground truth decompositions. Collecting and annotating such a dataset is an approach that cannot scale to sufficient variety and realism. We free ourselves from this limitation by training on unannotated images. Our method leverages the observation ...Conference Paper -
Iterative Deep Retinal Topology Extraction
(2018)Lecture Notes in Computer Science ~ Patch-Based Techniques in Medical ImagingConference Paper -
Acquiring Common Sense Spatial Knowledge Through Implicit Spatial Templates
(2018)Proceedings of 32nd AAAI Conference on Artificial IntelligenceConference Paper -
Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning
(2018)2018 IEEE/CVF Conference on Computer Vision and Pattern RecognitionThis paper tackles the problem of video object segmentation, given some user annotation which indicates the object of interest. The problem is formulated as pixel-wise retrieval in a learned embedding space: we embed pixels of the same object instance into the vicinity of each other, using a fully convolutional network trained by a modified triplet loss as the embedding model. Then the annotated pixels are set as reference and the rest ...Conference Paper -
ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes
(2018)2018 IEEE/CVF Conference on Computer Vision and Pattern RecognitionExploiting synthetic data to learn deep models has attracted increasing attention in recent years. However, the intrinsic domain difference between synthetic and real images usually causes a significant performance drop when applying the learned model to real world scenarios. This is mainly due to two reasons: 1) the model overfits to synthetic images, making the convolutional filters incompetent to extract informative representation for ...Conference Paper -
Appearance-and-Relation Networks for Video Classification
(2018)2018 IEEE/CVF Conference on Computer Vision and Pattern RecognitionConference Paper -
WILDTRACK: A Multi-camera HD Dataset for Dense Unscripted Pedestrian Detection
(2018)2018 IEEE/CVF Conference on Computer Vision and Pattern RecognitionPeople detection methods are highly sensitive to occlusions between pedestrians, which are extremely frequent in many situations where cameras have to be mounted at a limited height. The reduction of camera prices allows for the generalization of static multi-camera set-ups. Using joint visual information from multiple synchronized cameras gives the opportunity to improve detection performance. In this paper, we present a new large-scale ...Conference Paper -
Deep Extreme Cut: From Extreme Points to Object Segmentation
(2018)2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)This paper explores the use of extreme points in an object (left-most, right-most, top, bottom pixels) as input to obtain precise object segmentation for images and videos. We do so by adding an extra channel to the image in the input of a convolutional neural network (CNN), which contains a Gaussian centered in each of the extreme points. The CNN learns to transform this information into a segmentation of an object that matches those ...Conference Paper -
Classification-Driven Dynamic Image Enhancement
(2018)2018 IEEE/CVF Conference on Computer Vision and Pattern RecognitionConvolutional neural networks rely on image texture and structure to serve as discriminative features to classify the image content. Image enhancement techniques can be used as preprocessing steps to help improve the overall image quality and in turn improve the overall effectiveness of a CNN. Existing image enhancement methods, however, are designed to improve the perceptual quality of an image for a human observer. In this paper, we are ...Conference Paper -
Conditional Probability Models for Deep Image Compression
(2018)2018 IEEE/CVF Conference on Computer Vision and Pattern RecognitionDeep Neural Networks trained as image auto-encoders have recently emerged as a promising direction for advancing the state-of-the-art in image compression. The key challenge in learning such networks is twofold: To deal with quantization, and to control the trade-off between reconstruction error (distortion) and entropy (rate) of the latent image representation. In this paper, we focus on the latter challenge and propose a new technique ...Conference Paper