Related papers: Partial Coherence for Object Recognition and Depth…
Concealed object segmentation (COS) is a challenging task that involves localizing and segmenting those concealed objects that are visually blended with their surrounding environments. Despite achieving remarkable success, existing COS…
We develop the first (to the best of our knowledge) provably correct neural networks for a precise computational task, with the proof of correctness generated by an automated verification algorithm without any human input. Prior work on…
It is suggested that low-light image enhancement realizes one-to-many mapping since we have different definitions of NORMAL-light given application scenarios or users' aesthetic. However, most existing methods ignore subjectivity of the…
Sparse optical flow is widely used in various computer vision tasks, however assuming brightness consistency limits its performance in High Dynamic Range (HDR) environments. In this work, a lightweight network is used to extract…
Low-light image enhancement strives to improve the contrast, adjust the visibility, and restore the distortion in color and texture. Existing methods usually pay more attention to improving the visibility and contrast via increasing the…
Feature matching is a crucial task in the field of computer vision, which involves finding correspondences between images. Previous studies achieve remarkable performance using learning-based feature comparison. However, the pervasive…
Light field data has been demonstrated to facilitate the depth estimation task. Most learning-based methods estimate the depth infor-mation from EPI or sub-aperture images, while less methods pay attention to the focal stack. Existing…
A new theoretical technique for understanding, analyzing and developing optical systems is presented. The approach is statistical in nature, where information about an object under investigation is discovered, by examining deviations from a…
Both humans and computational methods struggle to discriminate the depths of objects hidden beneath foliage. However, such discrimination becomes feasible when we combine computational optical synthetic aperture sensing with the human…
The expanding applications, utilized by more users, enhance hardware performance and further develop cloud systems for big data processing. This leads to numerous unexplored deep learning applications, especially in advanced computer vision…
Discovering object-centric representations from images can significantly enhance the robustness, sample efficiency and generalizability of vision models. Works on images with multi-part objects typically follow an implicit object…
Optical vortex fields have applications in information processing and storage and in the manipulation of microscopic particles. We present analytic results for quantities describing the extent of spatial coherence and entropy of…
We present nonlinear photonic circuit models for constructing programmable linear transformations and use these to realize a coherent Perceptron, i.e., an all-optical linear classifier capable of learning the classification boundary…
An optical diffractive neural network (DNN) can be implemented with a cascaded phase mask architecture. Like an optical computer, the system can perform machine learning tasks such as number digit recognition in an all-optical manner.…
This article discusses how concepts and methods of complex networks can be applied to real-time imaging and computer vision. After a brief introduction of complex networks basic concepts, their use as means to represent and characterize…
In this work we study the mutual benefits of two common computer vision tasks, self-supervised depth estimation and semantic segmentation from images. For example, to help unsupervised monocular depth estimation, constraints from semantic…
Contrast enhancement and noise removal are coupled problems for low-light image enhancement. The existing Retinex based methods do not take the coupling relation into consideration, resulting in under or over-smoothing of the enhanced…
Depth estimation, as a necessary clue to convert 2D images into the 3D space, has been applied in many machine vision areas. However, to achieve an entire surrounding 360-degree geometric sensing, traditional stereo matching algorithms for…
This prospective study proposes CoMatch, a novel semi-dense image matcher with dynamic covisibility awareness and bilateral subpixel accuracy. Firstly, observing that modeling context interaction over the entire coarse feature map elicits…
Observing and recognizing materials is a fundamental part of our daily life. Under typical viewing conditions, we are capable of effortlessly identifying the objects that surround us and recognizing the materials they are made of.…