Related papers: Physically Grounded Monocular Depth via Nanophoton…
Wide-angle optical functionality is crucial for implementation of advanced imaging and image projection devices. Conventionally, wide-angle operation is attained by complicated assembly of multiple optical elements. Recent advances in…
Metalenses, owing to their ultra-thin planar structures, present a promising solution for reducing endoscopic invasiveness. However, achieving high-quality imaging with minimal invasiveness (short focal length of metalens) remains a…
Metasurfaces have attracted widespread attention due to an increasing demand of compact and wearable optical devices. For many applications, polarization-insensitive metasurfaces are highly desirable and appear to limit the choice of their…
Multifocal lens, which focus incident light at multiple foci, are widely used in imaging systems and optical communications. However, for the traditional design strategy, it combines several lenses that have different focal points into a…
The spiral phase contrast microscope can clearly distinguish the morphological information of the low contrast objects (i.e., biological samples) because of the isotropic edge-enhancement effect, while the bright field microscope can image…
Optical fiber is a well-established efficient way to guide and manipulate light and allowing high bandwidth optical transmission for long distance communication with low attenuation. Although a dielectric optical waveguide is efficient for…
Metric depth estimation from visual sensors is crucial for robots to perceive, navigate, and interact with their environment. Traditional range imaging setups, such as stereo or structured light cameras, face hassles including calibration,…
Monocular depth estimation is vital for scene understanding and downstream tasks. We focus on the supervised setup, in which ground-truth depth is available only at training time. Based on knowledge about the high regularity of real 3D…
Monocular depth estimation has applications in many fields, such as autonomous navigation and extended reality, making it an essential computer vision task. However, current methods often produce smooth depth maps that lack the fine…
Thanks to the compact design and multi-functional light-manipulation capabilities, reconfigurable metalenses, which consist of arrays of sub-wavelength meta-atoms, offer unique opportunities for advanced optical systems, from microscopy to…
Monocular depth estimation has recently progressed beyond ordinal depth to provide metric depth predictions. However, its reliability in underwater environments remains limited due to light attenuation and scattering, color distortion,…
As one of nanoscale planar structures, metasurface has shown excellent superiorities on manipulating light intensity, phase and/or polarization with specially designed nanoposts pattern. It allows to miniature a bulky optical lens into the…
Accurate monocular metric depth estimation (MMDE) is crucial to solving downstream tasks in 3D perception and modeling. However, the remarkable accuracy of recent MMDE methods is confined to their training domains. These methods fail to…
Obstructions such as raindrops, fences, or dust degrade captured images, especially when mechanical cleaning is infeasible. Conventional solutions to obstructions rely on a bulky compound optics array or computational inpainting, which…
We fabricated hybrid metal-dielectric nanoantennas and measured their optical response at three different wavelengths. The nanostructure is fabricated on a bilayer film formed by the sequential deposition of silicon and gold on a…
In many optical systems, including metal films, dielectric reflectors, and photonic crystals, electromagnetic waves can experience evanescent decay. The spatial length scale of such decay defines the penetration depth. The ability to reduce…
Monocular 3D object detection offers a low-cost alternative to LiDAR, yet remains less accurate due to the difficulty of estimating metric depth from a single image. We systematically evaluate how depth backbones and feature engineering…
In recent years, foundation models for monocular depth estimation have received increasing attention. Current methods mainly address typical daylight conditions, but their effectiveness notably decreases in low-light environments. There is…
This work addresses the task of zero-shot monocular depth estimation. A recent advance in this field has been the idea of utilising Text-to-Image foundation models, such as Stable Diffusion. Foundation models provide a rich and generic…
Dense and accurate depth estimation is essential for robotic manipulation, grasping, and navigation, yet currently available depth sensors are prone to errors on transparent, specular, and general non-Lambertian surfaces. To mitigate these…