检索结果-内蒙古大学图书馆

Self-supervised linear motion deblurring

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Peidong Janai, Joel Pollefeys, Marc Sattler, Torsten Geiger, Andreas Computer Vision and Geometry Group Department of Computer Science ETH Zürich Switzerland Autonomous Vision Group Max Planck Institute for Intelligent Systems Univeristy of Tübingen Tübingen Germany Microsoft Mixed Reality and Artificial Intelligence Lab Zürich Switzerland Computer Vision and Medical Image Analysis Group Chalmers University of Technology Sweden

Motion blurry images challenge many computer vision algorithms, e.g., feature detection, motion estimation, or object recognition. Deep convolutional neural networks are state-of-the-art for image deblurring. However, obtaining training data with corresponding sharp and blurry image pairs can be difficult. In this paper, we present a differentiable reblur model for self-supervised motion deblurring, which enables the network to learn from real-world blurry image sequences without relying on sharp images for supervision. Our key insight is that motion cues obtained from consecutive images yield sufficient information to inform the deblurring task. We therefore formulate deblurring as an inverse rendering problem, taking into account the physical image formation process: we first predict two deblurred images from which we estimate the corresponding optical flow. Using these predictions, we re-render the blurred images and minimize the difference with respect to the original blurry inputs. We use both synthetic and real dataset for experimental evaluations. Our experiments demonstrate that self-supervised single image deblurring is really feasible and leads to visually compelling results. Both the code and datasets are available at https://***/ethliup/SelfDeblur. Copyright © 2020, The Authors. All rights reserved.

关键词： Image enhancement

LongReMix: Robust Learning with High Confidence Samples in a Noisy label Environment

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cordeiro, Filipe R. Sachdeva, Ragav Belagiannis, Vasileios Reid, Ian Carneiro, Gustavo School of Computer Science Australian Institute for Machine Learning Australia Visual Geometry Group Department of Engineering Science University of Oxford United Kingdom Visual Computing Lab Department of Computing Universidade Federal Rural de Pernambuco Brazil Otto-von-Guericke-Universität Magdeburg Germany Centre for Vision Speech and Signal Processing University of Surrey United Kingdom

State-of-the-art noisy-label learning algorithms rely on an unsupervised learning to classify training samples as clean or noisy, followed by a semi-supervised learning (SSL) that minimises the empirical vicinal risk using a labelled set formed by samples classified as clean, and an unlabelled set with samples classified as noisy. The classification accuracy of such noisy-label learning methods depends on the precision of the unsupervised classification of clean and noisy samples, and the robustness of SSL to small clean sets. We address these points with a new noisy-label training algorithm, called LongReMix, which improves the precision of the unsupervised classification of clean and noisy samples and the robustness of SSL to small clean sets with a two-stage learning process. The stage one of LongReMix finds a small but precise high-confidence clean set, and stage two augments this high-confidence clean set with new clean samples and oversamples the clean data to increase the robustness of SSL to small clean sets. We test LongReMix on CIFAR-10 and CIFAR-100 with introduced synthetic noisy labels, and the real-world noisy-label benchmarks CNWL (Red Mini-ImageNet), Webvision, Clothing1M, and Food101-N. The results show that our LongReMix produces significantly better classification accuracy than competing approaches, particularly in high noise rate problems. Furthermore, our approach achieves state-of-the-art performance in most datasets. The code is available at https://***/filipe-research/LongReMix. © 2021, CC BY.

关键词： Deep learning

ScanMix: Learning from Severe label Noise via Semantic Clustering and Semi-Supervised Learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sachdeva, Ragav Cordeiro, Filipe Rolim Belagiannis, Vasileios Reid, Ian Carneiro, Gustavo Visual Geometry Group Department of Engineering Science University of Oxford United Kingdom School of Computer Science Australian Institute for Machine Learning Australia Visual Computing Lab Department of Computing Universidade Federal Rural de Pernambuco Brazil Otto-von-Guericke-Universität Magdeburg Germany Centre for Vision Speech and Signal Processing University of Surrey United Kingdom

We propose a new training algorithm, ScanMix, that explores semantic clustering and semi-supervised learning (SSL) to allow superior robustness to severe label noise and competitive robustness to non-severe label noise problems, in comparison to the state of the art (SOTA) methods. ScanMix is based on the expectation maximisation framework, where the E-step estimates the latent variable to cluster the training images based on their appearance and classification results, and the M-step optimises the SSL classification and learns effective feature representations via semantic clustering. We present a theoretical result that shows the correctness and convergence of ScanMix, and an empirical result that shows that ScanMix has SOTA results on CIFAR-10/-100 (with symmetric, asymmetric and semantic label noise), Red Mini-ImageNet (from the Controlled Noisy Web labels), Clothing1M and Webvision. In all benchmarks with severe label noise, our results are competitive to the current SOTA. © 2021, CC BY.

关键词： Semantics

Object finding in cluttered scenes using interactive perception

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Novkovic, Tonci Pautrat, Remi Furrer, Fadri Breyer, Michel Siegwart, Roland Nieto, Juan Autonomous Systems Lab ETH Zurich8092 Switzerland Computer Vision and Geometry Group ETH Zurich8092 Switzerland

Object finding in clutter is a skill that requires both perception of the environment and in many cases physical interaction. In robotics, interactive perception defines a set of algorithms that leverage actions to improve the perception of the environment, and vice versa use perception to guide the next action. Scene interactions are difficult to model, therefore, most of the current systems use predefined heuristics. This limits their ability to efficiently search for the target object in a complex environment. In order to remove heuristics and the need for explicit models of the interactions, in this work we propose a reinforcement learning based active and interactive perception system for scene exploration and object search. We evaluate our work both in simulated and in real world experiments using a robotic manipulator equipped with an RGB and a depth camera, and compared our system to two baselines. The results indicate that our approach, trained in simulation only, transfers smoothly to reality and can solve the object finding task efficiently and with more than 90% success rate. Copyright © 2019, The Authors. All rights reserved.

关键词： Robotics

RayNet: Learning volumetric 3d reconstruction with ray potentials

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Paschalidou, Despoina Ulusoy, Ali Osman Schmitt, Carolin Van Gool, Luc Geiger, Andreas Autonomous Vision Group MPI for Intelligent Systems Tübingen Microsoft Computer Vision Lab ETH Zürich KU Leuven Computer Vision and Geometry Group ETH Zürich Max Planck ETH Center for Learning Systems

In this paper, we consider the problem of reconstructing a dense 3D model using images captured from different views. Recent methods based on convolutional neural networks (CNN) allow learning the entire task from data. However, they do not incorporate the physics of image formation such as perspective geometry and occlusion. Instead, classical approaches based on Markov Random Fields (MRF) with ray-potentials explicitly model these physical processes, but they cannot cope with large surface appearance variations across different viewpoints. In this paper, we propose RayNet, which combines the strengths of both frameworks. RayNet integrates a CNN that learns view-invariant feature representations with an MRF that explicitly encodes the physics of perspective projection and occlusion. We train RayNet end-to-end using empirical risk minimization. We thoroughly evaluate our approach on challenging real-world datasets and demonstrate its benefits over a piece-wise trained baseline, hand-crafted models as well as other learning-based approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Image reconstruction

Visual Feature Attribution Using Wasserstein GANs

学校读者我要写书评

暂无评论

Visual Feature Attribution Using Wasserstein GANs

Conference on computer vision and Pattern Recognition (CVPR)

作者： Christian F. Baumgartner Lisa M. Koch Kerem Can Tezcan Jia Xi Ang Ender Konukoglu Computer Vision Lab ETH Zurich Computer Vision and Geometry Group ETH Zurich Computer Vision Lab ETH Zurich Zurich Switzerland

Attributing the pixels of an input image to a certain category is an important and well-studied problem in computer vision, with applications ranging from weakly supervised localisation to understanding hidden effects in the data. In recent years, approaches based on interpreting a previously trained neural network classifier have become the de facto state-of-the-art and are commonly used on medical as well as natural image datasets. In this paper, we discuss a limitation of these approaches which may lead to only a subset of the category specific features being detected. To address this problem we develop a novel feature attribution technique based on Wasserstein Generative Adversarial Networks (WGAN), which does not suffer from this limitation. We show that our proposed method performs substantially better than the state-of-the-art for visual attribution on a synthetic dataset and on real 3D neuroimaging data from patients with mild cognitive impairment (MCI) and Alzheimer's disease (AD). For AD patients the method produces compellingly realistic disease effect maps which are very close to the observed effects.

关键词： Visualization Biomedical imaging Gallium nitride Alzheimer's disease Neural networks Neuroimaging

Large-Scale, Real-Time Visual-Inertial localization revisited

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Lynen, Simon Zeisl, Bernhard Aiger, Dror Bosse, Michael Hesch, Joel Pollefeys, Marc Siegwart, Roland Sattler, Torsten Google Switzerland Zurich Switzerland Google Israel Tel Aviv Israel Autonomous Systems Lab ETH Zurich Computer Vision and Geometry Group Department of Computer Science ETH Zurich Department of Microsoft Department of Electrical Engineering Chalmers University of Technology

The overarching goals in image-based localization are scale, robustness and speed. In recent years, approaches based on local features and sparse 3D point-cloud models have both dominated the benchmarks and seen successful realworld deployment. They enable applications ranging from robot navigation, autonomous driving, virtual and augmented reality to device geo-localization. Recently end-to-end learned localization approaches have been proposed which show promising results on small scale datasets. However the positioning accuracy, scalability, latency and compute & storage requirements of these approaches remain open challenges. We aim to deploy localization at global-scale where one thus relies on methods using local features and sparse 3D models. Our approach spans from offline model building to real-time client-side pose fusion. The system compresses appearance and geometry of the scene for efficient model storage and lookup leading to scalability beyond what what has been previously demonstrated. It allows for low-latency localization queries and efficient fusion run in real-time on mobile platforms by combining server-side localization with real-time visual-inertial-based camera pose tracking. In order to further improve efficiency we leverage a combination of priors, nearest neighbor search, geometric match culling and a cascaded pose candidate refinement step. This combination outperforms previous approaches when working with large scale models and allows deployment at unprecedented scale. We demonstrate the effectiveness of our approach on a proof-of-concept system localizing 2.5 million images against models from four cities in different regions on the world achieving query latencies in the 200ms range. Copyright © 2019, The Authors. All rights reserved.

关键词： Nearest neighbor search

Learning to segment medical images with scribble-supervision alone

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Can, Yigit B. Chaitanya, Krishna Mustafa, Basil Koch, Lisa M. Konukoglu, Ender Baumgartner, Christian F. Computer Vision Lab ETH Zurich Switzerland Computer Vision and Geometry Group ETH Zurich Switzerland University of Cambridge United Kingdom

Semantic segmentation of medical images is a crucial step for the quantification of healthy anatomy and diseases alike. The majority of the current state-of-the-art segmentation algorithms are based on deep neural networks and rely on large datasets with full pixel-wise annotations. Producing such annotations can often only be done by medical professionals and requires large amounts of valuable time. Training a medical image segmentation network with weak annotations remains a relatively unexplored topic. In this work we investigate training strategies to learn the parameters of a pixel-wise segmentation network from scribble annotations alone. We evaluate the techniques on public cardiac (ACDC) and prostate (NCI-ISBI) segmentation datasets. We find that the networks trained on scribbles suffer from a remarkably small degradation in Dice of only 2.9% (cardiac) and 4.5% (prostate) with respect to a network trained on full annotations. Copyright © 2018, The Authors. All rights reserved.

关键词： Urology

Real-time stereo matching failure prediction and resolution using orthogonal stereo setups

学校读者我要写书评

暂无评论

Real-time stereo matching failure prediction and resolution ...

2017 IEEE International Conference on Robotics and Automation, ICRA 2017

作者： Meier, Lorenz Honegger, Dominik Vilhjalmsson, Vilhjalmur Pollefeys, Marc Computer Vision and Geometry Lab Institute for Visual Computing Computer Science Department ETH Zurich Zurich8092 Switzerland

ISBN: (纸本)9781509046331

Estimating the depth from two images with a baseline has a well-known regular problem: When a line is parallel to the epipolar geometry it is not possible to estimate the depth from pixels on this line. Moreover, the classic measure for the certainty of the depth estimate fails as well: The matching score between the template and any pixel on the epipolar line is perfect. This results for common scenes in incorrect matches with very high confidence, some even resistant to left-right image checks. It is straightforward to try to address this by adding a second stereo head in a perpendicular direction. However, it is nontrivial to identify the failure and fuse the two depth maps in a real-time system. A simple weighted average will alleviate the problem but still result in a very large error in the depth map. Our contributions are: 1) We derive a model to predict the failure of stereo by leveraging the matching scores and 2) we propose a combined cost function to fuse two depth maps from orthogonal stereo heads using the failure prediction, matching score and consistency. We show the resulting system in real-time operation on a low-latency system in indoor, urban and natural environments. © 2017 IEEE.

关键词： Pixels