Related papers: Omnidirectional MediA Format (OMAF): Toolbox for V…
The development of optical nanofibers (ONF) and the study and control of their optical properties when coupling atoms to their electromagnetic modes has opened new possibilities for their use in quantum optics and quantum information…
Notable breakthroughs in unified understanding and generation modeling have led to remarkable advancements in image understanding, reasoning, production and editing, yet current foundational models predominantly focus on processing images,…
Panoramic imagery, with its 360{\deg} field of view, offers comprehensive information to support Multi-Object Tracking (MOT) in capturing spatial and temporal relationships of surrounding objects. However, most MOT algorithms are tailored…
The real world is dynamic, yet most image fusion methods process static frames independently, ignoring temporal correlations in videos and leading to flickering and temporal inconsistency. To address this, we propose Unified Video Fusion…
3D reconstruction from images has wide applications in Virtual Reality and Automatic Driving, where the precision requirement is very high. Ground-breaking research in the neural radiance field (NeRF) by utilizing Multi-Layer Perceptions…
Neural implicit fields have established a new paradigm for scene representation, with subsequent work achieving high-quality real-time rendering. However, reconstructing 3D scenes from oblique aerial photography presents unique challenges,…
Optical flow estimation is very challenging in situations with transparent or occluded objects. In this work, we address these challenges at the task level by introducing Amodal Optical Flow, which integrates optical flow with amodal…
In this survey, we analyze the newest machine learning (ML) techniques for optical orthogonal frequency division multiplexing (O-OFDM)-based optical communications. ML has been proposed to mitigate channel and transceiver imperfections. For…
Orthogonal time frequency space (OTFS) is a two-dimensional modulation technique that uses the delay-Doppler (DD) domain and is a candidate for providing robust, high-capacity wireless communications for envisioned 6G and beyond networks.…
Current tomographic imaging systems need major improvements, especially when multi-dimensional, multi-scale, multi-temporal and multi-parametric phenomena are under investigation. Both preclinical and clinical imaging now depend on in vivo…
Recently, a camera or an image sensor receiver based optical wireless communications (OWC) techniques have attracted particular interest in areas such as the internet of things, indoor localization, motion capture, and intelligent…
This paper presents OmniVL, a new foundation model to support both image-language and video-language tasks using one universal architecture. It adopts a unified transformer-based visual encoder for both image and video inputs, and thus can…
We consider outdoor optical access points (OAPs), which, enabled by recent advances in metasurface technology, have attracted growing interest. While OAPs promise high data rates and strong physical-layer security, practical deployments…
Wide field-of-view (FoV) LiDAR sensors provide dense geometry across large environments, but existing LiDAR-inertial-visual odometry (LIVO) systems generally rely on a single camera, limiting their ability to fully exploit LiDAR-derived…
Next-generation wireless networks require enhanced flexibility, efficiency, and reliability in physical layer waveform design to address the challenges posed by heterogeneous channel conditions and stringent quality-of-service demands. To…
Recently, by introducing large-scale dataset and strong transformer network, video-language pre-training has shown great success especially for retrieval. Yet, existing video-language transformer models do not explicitly fine-grained…
This paper describes the OI Exchange Format, a standard for exchanging calibrated data from optical (visible/infrared) stellar interferometers. The standard is based on the Flexible Image Transport System (FITS), and supports storage of the…
This paper presents a multimodal indoor odometry dataset, OdomBeyondVision, featuring multiple sensors across the different spectrum and collected with different mobile platforms. Not only does OdomBeyondVision contain the traditional…
In the era of big data, it is becoming common to have data with multiple modalities or coming from multiple sources, known as "multi-view data". Multi-view data are usually unlabeled and come from high-dimensional spaces (such as language…
Contemporary Virtual Reality (VR) setups commonly consist of a Head-Mounted Display (HMD) tethered to a content-generating server. "Cutting the wire" in such setups and going truly wireless will require a wireless network capable of…