Related papers: RUN: Reversible Unfolding Network for Concealed Ob…
Programmable metasurfaces and adjustable antennas are promising technologies. The security of a rotatable array system is investigated in this paper. A dual-base-station (BS) architecture is adopted, in which the BSs collaboratively perform…
Referring Image Segmentation (RIS) is a fundamental vision-language task that outputs object masks based on text descriptions. Many works have achieved considerable progress for RIS, including different fusion method designs. In this work,…
In this paper, we consider deep neural networks for solving inverse problems that are robust to forward model mis-specifications. Specifically, we treat sensing problems with model mismatch where one wishes to recover a sparse…
Object detection and instance segmentation are two fundamental computer vision tasks. They are closely correlated but their relations have not yet been fully explored in most previous work. This paper presents RDSNet, a novel deep…
Automated waste recycling aims to efficiently separate the recyclable objects from the waste by employing vision-based systems. However, the presence of varying shaped objects having different material types makes it a challenging problem,…
Image rescaling is a commonly used bidirectional operation, which first downscales high-resolution images to fit various display screens or to be storage- and bandwidth-friendly, and afterward upscales the corresponding low-resolution…
Referring Remote Sensing Image Segmentation (RRSIS) is a new challenge that combines computer vision and natural language processing, delineating specific regions in aerial images as described by textual queries. Traditional Referring Image…
Camouflaged object segmentation presents unique challenges compared to traditional segmentation tasks, primarily due to the high similarity in patterns and colors between camouflaged objects and their backgrounds. Effective solutions to…
Non-line-of-sight (NLOS) imaging aims at reconstructing targets obscured from the direct line of sight. Existing NLOS imaging algorithms require dense measurements at rectangular grid points in a large area of the relay surface, which…
Reconstructing an object's shape and appearance in terms of a mesh textured by a spatially-varying bidirectional reflectance distribution function (SVBRDF) from a limited set of images captured under collocated light is an ill-posed…
Existing time-resolved non-line-of-sight (NLOS) imaging methods reconstruct hidden scenes by inverting the optical paths of indirect illumination measured at visible relay surfaces. These methods are prone to reconstruction artifacts due to…
We introduce a novel robotic system for improving unseen object instance segmentation in the real world by leveraging long-term robot interaction with objects. Previous approaches either grasp or push an object and then obtain the…
Text-prompted image segmentation enables fine-grained visual understanding and is critical for applications such as human-computer interaction and robotics. However, existing supervised fine-tuning methods typically ignore explicit…
Referring Image Segmentation (RIS) is a challenging task that requires an algorithm to segment objects referred by free-form language expressions. Despite significant progress in recent years, most state-of-the-art (SOTA) methods still…
Indoor traversability segmentation aims to identify safe, navigable free space for autonomous agents, which is critical for robotic navigation. Pure vision-based models often fail to detect thin obstacles, such as chair legs, which can pose…
Capsule networks promise significant benefits over convolutional networks by storing stronger internal representations, and routing information based on the agreement between intermediate representations' projections. Despite this, their…
This paper addresses the challenge of perceiving complete object shapes through visual perception. While prior studies have demonstrated encouraging outcomes in segmenting the visible parts of objects within a scene, amodal segmentation, in…
Reliable downlink communication in satellite-to-underground networks remains challenging due to severe signal attenuation caused by underground soil and refraction in the air-soil interface. To address this, we propose a novel cooperative…
Object segmentation is a crucial problem that is usually solved by using supervised learning approaches over very large datasets composed of both images and corresponding object masks. Since the masks have to be provided at pixel level,…
Is it possible to restructure the non-linear activation functions in a deep network to create hardware-efficient models? To address this question, we propose a new paradigm called Restructurable Activation Networks (RANs) that manipulate…