Related papers: Physically Grounded Monocular Depth via Nanophoton…
Metalenses are optical devices that implement nanostructures as phase shifters to focus incident light. Their compactness and simple fabrication make them a potential cost-effective solution for increasing light collection efficiency in…
We introduce MapAnything, a unified transformer-based feed-forward model that ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, depth, or partial reconstructions, and then directly regresses…
Nanoparticle-on-mirror plasmonic nanocavities, capable of extreme optical confinement and enhancement, have triggered state-of-the-art progress in nanophotonics and development of applications in enhanced spectroscopies and molecular…
Perceiving 3D information is of paramount importance in many applications of computer vision. Recent advances in monocular depth estimation have shown that gaining such knowledge from a single camera input is possible by training deep…
Varifocal lenses are essential components of dynamic optical systems with applications in photography, mixed reality, and microscopy. Metasurface optics has strong potential for creating tunable flat optics. Existing tunable metalenses,…
Self-supervised monocular depth estimation has been widely investigated to estimate depth images and relative poses from RGB images. This framework is attractive for researchers because the depth and pose networks can be trained from just…
Over the past few years, self-supervised monocular depth estimation that does not depend on ground-truth during the training phase has received widespread attention. Most efforts focus on designing different types of network architectures…
The metalenses have been extensively studied for their compact and flexible characteristics in focusing and imaging applications. However, it remains a significant challenge to design a broadband achromatic metalens that maintains high…
Nanoporous media exhibit structures significantly smaller than the wavelengths of visible light and can thus act as photonic metamaterials. Their optical functionality is not determined by the properties of the base materials, but rather by…
Plenoptic imaging enables a light-field to be captured by a single monocular objective lens and an array of micro lenses attached to an image sensor. Metric distances of the light-field's depth planes remain unapparent prior to acquisition.…
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…
Monocular depth estimation, enabled by self-supervised learning, is a key technique for 3D perception in computer vision. However, it faces significant challenges in real-world scenarios, which encompass adverse weather variations, motion…
Monocular depth estimation has drawn widespread attention from the vision community due to its broad applications. In this paper, we propose a novel physics (geometry)-driven deep learning framework for monocular depth estimation by…
Underwater monocular depth estimation serves as the foundation for tasks such as 3D reconstruction of underwater scenes. However, due to the influence of light and medium, the underwater environment undergoes a distinctive imaging process,…
Metasurface lenses, namely metalenses, are ultrathin planar nanostructures that are capable of manipulating the properties of incoming light and imparting lens-like wavefront to the output. Although they have shown promising potentials for…
Sensing light's polarization and wavefront direction enables surface curvature assessment, material identification, shadow differentiation, and improved image quality in turbid environments. Traditional polarization cameras utilize multiple…
Over the past decade, multi-element superconducting nanowire single-photon detectors (SNSPDs) have emerged as the leading single-photon detection technology due to their exceptional system detection efficiency (SDE), ultrahigh timing…
Structuring light emission from single-photon emitters in multiple degrees of freedom is of a great importance for quantum information processing towards higher dimensions. However, traditional control of emission from quantum light sources…
Achieving high-fidelity, compact RGBD imaging presents a dual challenge: conventional compact optics struggle with RGB sharpness across the entire depth-of-field, while software-only Monocular Depth Estimation (MDE) is an ill-posed problem…
Metalens, as the most promising and applicable emerging optical device, has long been constrained by the limited field of view (FOV). Recent studies employing phase engineering or multi-layer strategies have made some progress, but they all…