Related papers: MP-PolarMask: A Faster and Finer Instance Segmenta…
We study the challenging problem of unsupervised multi-object segmentation on single images. Existing methods, which rely on image reconstruction objectives to learn objectness or leverage pretrained image features to group similar pixels,…
Accurately measuring the geometry and spatially-varying reflectance of real-world objects is a complex task due to their intricate shapes formed by concave features, hollow engravings and diverse surfaces, resulting in inter-reflection and…
The reliability of grasp detection for target objects in complex scenes is a challenging task and a critical problem that needs to be solved urgently in practical application. At present, the grasp detection location comes from searching…
Polarization cameras can capture multiple polarized images with different polarizer angles in a single shot, bringing convenience to polarization-based downstream tasks. However, their direct outputs are color-polarization filter array…
In this work, we present a new operator, called Instance Mask Projection (IMP), which projects a predicted Instance Segmentation as a new feature for semantic segmentation. It also supports back propagation so is trainable end-to-end. Our…
This work demonstrates nanoscale magnetic imaging using bright circularly polarized high-harmonic radiation. We utilize the magneto-optical contrast of worm-like magnetic domains in a Co/Pd multilayer structure, obtaining quantitative…
Over the last decade, the light microscope has become increasingly useful as a quantitative tool for studying colloidal systems. The ability to obtain particle coordinates in bulk samples from micrographs is particularly appealing. In this…
Object detection and instance segmentation in remote sensing images is a fundamental and challenging task, due to the complexity of scenes and targets. The latest methods tried to take into account both the efficiency and the accuracy of…
Coronagraph instruments on future space telescopes will enable the direct detection and characterization of Earth-like exoplanets around Sun-like stars for the first time. The quest for the optimal optical coronagraph designs has made rapid…
Light has many properties that vision sensors can passively measure. Colour-band separated wavelength and intensity are arguably the most commonly used for monocular 6D object pose estimation. This paper explores how complementary…
This paper describes AutoFocus, an efficient multi-scale inference algorithm for deep-learning based object detectors. Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions…
The polarization of light conveys crucial information about the spatial ordering and optical properties of a specimen. However, precise polarization measurement in challenging conditions, including constrained spaces, low light levels, and…
Accurately modeling how real-world materials reflect light remains a core challenge in inverse rendering, largely due to the scarcity of real measured reflectance data. Existing approaches rely heavily on synthetic datasets with simplified…
In this work, we tackle the problem of instance segmentation, the task of simultaneously solving object detection and semantic segmentation. Towards this goal, we present a model, called MaskLab, which produces three outputs: box detection,…
Polarization information of the light can provide rich cues for computer vision and scene understanding tasks, such as the type of material, pose, and shape of the objects. With the advent of new and cheap polarimetric sensors, this imaging…
Purpose: Magnetic polarizability tensors (MPTs) provide an economical characterisation of conducting magnetic metallic objects and their spectral signature can aid in the solution of metal detection inverse problems, such as scrap metal…
Monocular surface normal estimators trained on large-scale RGB-normal data often perform poorly in the edge cases of reflective, textureless, and dark surfaces. Polarization encodes surface orientation independently of texture and albedo,…
Polarization-resolved near-infrared imaging adds a useful optical contrast mechanism to eye tracking by measuring the polarization state of light reflected by ocular tissues in addition to its intensity. In this paper we demonstrate how…
Medical image segmentation is the technique that helps doctor view and has a precise diagnosis, particularly in Colorectal Cancer. Specifically, with the increase in cases, the diagnosis and identification need to be faster and more…
The shapelets method for image analysis is based upon the decomposition of localised objects into a series of orthogonal components with convenient mathematical properties. We extend the "Cartesian shapelet" formalism from earlier work, and…