A5073866871- Cell Image Analysis Techniques
- Image Processing Techniques and Applications
- Image and Signal Denoising Methods
- Robotics and Sensor-Based Localization
- Advanced Neural Network Applications
- AI in cancer detection
- Advanced Vision and Imaging
- Advanced Fluorescence Microscopy Techniques
- Microtubule and mitosis dynamics
- Image and Object Detection Techniques
- Photosynthetic Processes and Mechanisms
- Advanced Image Processing Techniques
- Advanced Image and Video Retrieval Techniques
- Human Pose and Action Recognition
- Photoacoustic and Ultrasonic Imaging
- Radiomics and Machine Learning in Medical Imaging
- Industrial Vision Systems and Defect Detection
- CAR-T cell therapy research
- Advanced Electron Microscopy Techniques and Applications
- Fungal and yeast genetics research
- Environmental Monitoring and Data Management
- Lung Cancer Diagnosis and Treatment
- Biosimilars and Bioanalytical Methods
- Atmospheric and Environmental Gas Dynamics
- Robot Manipulation and Learning
University of Birmingham
2021-2025
University of Nottingham
2024
The Ohio State University Wexner Medical Center
2024
The Ohio State University
2024
The Ohio State University Comprehensive Cancer Center – Arthur G. James Cancer Hospital and Richard J. Solove Research Institute
2024
Max Planck Institute of Molecular Cell Biology and Genetics
2012-2021
Center for Systems Biology Dresden
2019-2021
Max Planck Institute for Physics
2020
Max Planck Institute for the Physics of Complex Systems
2019-2020
TU Dresden
2014-2017
The field of image denoising is currently dominated by discriminative deep learning methods that are trained on pairs noisy input and clean target images. Recently it has been shown such can also be without targets. Instead, independent images used, in an approach known as Noise2Noise (N2N). Here, we introduce Noise2Void (N2V), a training scheme takes this idea one step further. It does not require pairs, nor Consequently, N2V allows us to train directly the body data denoised therefore...
RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally hand-crafted pipelines have been replaced by deep learning pipelines, which can be trained end-to-end fashion. However, has so far not used as part of such because its hypothesis selection procedure non-differentiable. this work, we present two different ways to overcome limitation. The most promising approach inspired reinforcement...
In recent years, the task of estimating 6D pose object instances and complete scenes, i.e. camera localization, from a single input image has received considerable attention. Consumer RGB-D cameras have made this feasible, even for difficult, texture-less objects scenes. work, we show that RGB is sufficient to achieve visually convincing results. Our key concept model exploit uncertainty system at all stages processing pipeline. The comes in form continuous distributions over 3D coordinates...
Abstract Deep Learning (DL) methods are powerful analytical tools for microscopy and can outperform conventional image processing pipelines. Despite the enthusiasm innovations fuelled by DL technology, need to access compatible resources train networks leads an accessibility barrier that novice users often find difficult overcome. Here, we present ZeroCostDL4Mic, entry-level platform simplifying leveraging free, cloud-based computational of Google Colab. ZeroCostDL4Mic allows researchers...
Analysis-by-synthesis has been a successful approach for many tasks in computer vision, such as 6D pose estimation of an object RGB-D image which is the topic this work. The idea to compare observation with output forward process, rendered interest particular pose. Due occlusion or complicated sensor noise, it can be difficult perform comparison meaningful way. We propose that "learns compare", while taking these difficulties into account. This done by describing posterior density...
This paper addresses the task of estimating 6D-pose a known 3D object from single RGB-D image. Most modern approaches solve this in three steps: i) compute local features, ii) generate pool pose-hypotheses, iii) select and refine pose pool. work focuses on second step. While all existing hypotheses via reasoning, e.g. RANSAC or Hough-Voting, we are first to show that global reasoning is beneficial at stage. In particular, formulate novel fully-connected Conditional Random Field (CRF) outputs...
Abstract Scanning probe microscopy (SPM) has revolutionized the fields of materials, nano-science, chemistry, and biology, by enabling mapping surface properties manipulation with atomic precision. However, these achievements require constant human supervision; fully automated SPM not been accomplished yet. Here we demonstrate an artificial intelligence framework based on machine learning for autonomous operation (DeepSPM). DeepSPM includes algorithmic search good sample regions, a...
Today, Convolutional Neural Networks (CNNs) are the leading method for image denoising. They traditionally trained on pairs of images, which often hard to obtain practical applications. This motivates self-supervised training methods such as Noise2Void (N2V) that operate single noisy images. Self-supervised are, unfortunately, not competitive with models pairs. Here, we present Probabilistic (PN2V), a train CNNs predict per-pixel intensity distributions. Combining these suitable description...
This work addresses the task of camera localization in a known 3D scene given single input RGB image. State-of-the-art approaches accomplish this two steps: firstly, regressing for every pixel image its coordinate and subsequently, using these coordinates to estimate final 6D pose via RANSAC. To solve first step. Random Forests (RFs) are typically used. On other hand. Neural Networks (NNs) reign many dense regression tasks, but not test-time efficient. We ask question: which is best...
Removal of noise from fluorescence microscopy images is an important first step in many biological analysis pipelines. Current state-of-the-art supervised methods employ convolutional neural networks that are trained with clean (ground-truth) images. Recently, it was shown self-supervised image denoising blind spot achieves excellent performance even when ground-truth not available, as common microscopy. However, these approaches, e.g. Noise2Void (N2V), generally assume pixel-wise...
The large-scale multiparametric analysis of individual nanoparticles is increasingly vital in the diverse fields biology, medicine, and materials science. However, current methods struggle with tradeoff between measurement scalability sensitivity, especially when identifying rare heterogeneous mixtures. By developing combining an unsupervised deep learning-based denoising method optofluidic device tuned for nanoparticle detection, we realize a analyzer that simultaneously achieves high...
State-of-the-art computer vision algorithms often achieve efficiency by making discrete choices about which hypotheses to explore next. This allows allocation of computational resources promising candidates, however, such decisions are non-differentiable. As a result, these hard train in an end-to-end fashion. In this work we propose learn efficient algorithm for the task 6D object pose estimation. Our system optimizes parameters existing state-of-the art estimation using reinforcement...
Accurate pose estimation of object instances is a key aspect in many applications, including augmented reality or robotics. For example, task domestic robot could be to fetch an item from open drawer. The poses both, the drawer and have known by order fulfil task. 6D rigid objects has been addressed with great success recent years. In large part, this due advent consumer-level RGB-D cameras, which provide rich, robust input data. However, practical use state-of-the-art approaches limited...
In cell biology and other fields the automatic accurate localization of sub-resolution objects in images is an important tool. The signal often corrupted by multiple forms noise, including excess noise resulting from amplification electron multiplying charge-coupled device (EMCCD). Here we present our novel Nested Maximum Likelihood Algorithm (NMLA), which solves problem localizing overlapping emitters a setting affected repeatedly solving task independent for single noise-free system. NMLA...
The field of image denoising is currently dominated by discriminative deep learning methods that are trained on pairs noisy input and clean target images. Recently it has been shown such can also be without targets. Instead, independent images used, in an approach known as Noise2Noise (N2N). Here, we introduce Noise2Void (N2V), a training scheme takes this idea one step further. It does not require pairs, nor Consequently, N2V allows us to train directly the body data denoised therefore...