Related papers: Neural 360$^\circ$ Structured Light with Learned M…

We introduce a novel technique for designing color filter metasurfaces using a data-driven approach based on deep learning. Our innovative approach employs inverse design principles to identify highly efficient designs that outperform all…

Despite remarkable progress in computer vision, modern recognition systems remain fundamentally limited by their dependence on rich, redundant visual inputs. In contrast, humans can effortlessly understand sparse, minimal representations…

Three-dimensional (3D) object reconstruction based on differentiable rendering (DR) is an active research topic in computer vision. DR-based methods minimize the difference between the rendered and target images by optimizing both the shape…

Recent point-based differentiable rendering techniques have achieved significant success in high-fidelity reconstruction and fast rendering. However, due to the unstructured nature of point-based representations, they are difficult to apply…

Tailoring the degrees of freedom (DoF) of light for a desired purpose, so-called structured light, has delivered numerous advances over the past decade, ranging from communications and quantum cryptography to optical trapping, and…

Despite significant advances in the field of freeform optical design, there still remain various unsolved problems. One of these is the design of smooth, shallow freeform topologies, consisting of multiple convex, concave and saddle shaped…

Neural radiance fields (NeRFs) have recently emerged as a promising approach for 3D reconstruction and novel view synthesis. However, NeRF-based methods encode shape, reflectance, and illumination implicitly and this makes it challenging…

Metasurfaces have been used to realize optical functions such as focusing and beam steering. They use sub-wavelength nanostructures to control the local amplitude and phase of light. Here we show that such control could also enable a new…

Nanostructured materials have recently emerged as a promising approach for material appearance design. Research has mainly focused on creating structural colours by wave interference, leaving aside other important aspects that constitute…

Despite their impressive performance, contemporary neural networks often lack structural safeguards that promote stable learning and interpretable behavior. In this work, we introduce a reformulation of layer-level transformations that…

Recovering the 3D shape of transparent objects using a small number of unconstrained natural images is an ill-posed problem. Complex light paths induced by refraction and reflection have prevented both traditional and deep multiview stereo…

We consider the problem of active 3D imaging using single-shot structured light systems, which are widely employed in commercial 3D sensing devices such as Apple Face ID and Intel RealSense. Traditional structured light methods typically…

The fusion of rigorous physical laws with flexible data-driven learning represents a new frontier in scientific simulation, yet bridging the gap between physical interpretability and computational efficiency remains a grand challenge. In…

Metasurfaces play a key role in functionalizing light at the nanoscale. Existing dielectric metasurfaces, however, are often limited to geometric primitives and their usage in emergent hybrid metasurfaces is hampered as confinement of light…

Recently, end-to-end trainable deep neural networks have significantly improved stereo depth estimation for perspective images. However, 360{\deg} images captured under equirectangular projection cannot benefit from directly adopting…

We introduce a novel depth estimation technique for multi-frame structured light setups using neural implicit representations of 3D space. Our approach employs a neural signed distance field (SDF), trained through self-supervised…

Metasurfaces are ultrathin, engineered materials composed of nanostructures that manipulate light in ways unattainable by natural materials. Recent advances have leveraged computational optimization, machine learning, and deep learning to…

Deploying advanced imaging solutions to robotic and autonomous systems by mimicking human vision requires simultaneous acquisition of multiple fields of views, named the peripheral and fovea regions. Low-resolution peripheral field provides…

Neural representations have emerged as a new paradigm for applications in rendering, imaging, geometric modeling, and simulation. Compared to traditional representations such as meshes, point clouds, or volumes they can be flexibly…

Structured light has proven useful for numerous photonic applications. However, the current use of structured light in optical fiber science and technology is severely limited by mode mixing or by the lack of optical elements that can be…