Related papers: Neural 360$^\circ$ Structured Light with Learned M…
Nano-optic imagers that modulate light at sub-wavelength scales could unlock unprecedented applications in diverse domains ranging from robotics to medicine. Although metasurface optics offer a path to such ultra-small imagers, existing…
Recent illumination estimation methods have focused on enhancing the resolution and improving the quality and diversity of the generated textures. However, few have explored tailoring the neural network architecture to the Equirectangular…
Recent advances in neural rendering have shown great potential for reconstructing scenes from multiview images. However, accurately representing objects with glossy surfaces remains a challenge for existing methods. In this work, we…
Metasurfaces, typically realized as arrays of nanopillars, transform electromagnetic (EM) fields depending on their geometry and spatial arrangement. For solving the inverse problem of designing new metasurfaces that transform EM fields in…
A long-standing goal in scene understanding is to obtain interpretable and editable representations that can be directly constructed from a raw monocular RGB-D video, without requiring specialized hardware setup or priors. The problem is…
Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion. Recent NeRF based methods achieve impressive fidelity of 3D reconstruction, but bake…
Flexible control light field across multiple parameters is the cornerstone of versatile and miniaturized optical devices. Metasurfaces, comprising subwavelength scatterers, offer a potent platform for executing such precise manipulations.…
For a monocular 360 image, depth estimation is a challenging because the distortion increases along the latitude. To perceive the distortion, existing methods devote to designing a deep and complex network architecture. In this paper, we…
Virtual reality and augmented reality (XR) bring increasing demand for 3D content. However, creating high-quality 3D content requires tedious work that a human expert must do. In this work, we study the challenging task of lifting a single…
360 cameras capture the entire surrounding environment with a large FoV, exhibiting comprehensive visual information to directly infer the 3D structures, e.g., depth and surface normal, and semantic information simultaneously. Existing…
Optical flow computation is essential in the early stages of the video processing pipeline. This paper focuses on a less explored problem in this area, the 360$^\circ$ optical flow estimation using deep neural networks to support…
In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape. Recent works represent 3D surfaces implicitly with a Neural Network, thereby breaking previous barriers in…
Dense reconstruction and differentiable rendering are fundamental tightly connected operations in 3D vision and computer graphics. Recent neural implicit representations demonstrate compelling advantages in reconstruction fidelity and…
Structural coloration is commonly modeled using wave optics for reliable and photorealistic rendering of natural, quasi-periodic and complex nanostructures. Such models often rely on dense, preliminary or preprocessed data to accurately…
Deep learning based rendering has achieved major improvements in photo-realistic image synthesis, with potential applications including visual effects in movies and photo-realistic scene building in video games. However, a significant…
Resonant metasurfaces are of paramount importance in addressing the growing demand for reduced thickness and complexity, while ensuring high optical efficiency. This becomes particularly crucial in overcoming fabrication challenges…
Relying on either deep models or physical models are two mainstream approaches for solving inverse sample reconstruction problems in programmable illumination computational microscopy. Solutions based on physical models possess strong…
Artificial intelligence has revolutionized optical device design, overcoming the efficiency bottlenecks of traditional methods. For holographic metasurfaces, conventional iterative algorithms suffer from time-consuming iterations and…
Despite recent breakthroughs in deep learning methods for image lighting enhancement, they are inferior when applied to portraits because 3D facial information is ignored in their models. To address this, we present a novel deep learning…
Visual perception relies on inference of 3D scene properties such as shape, pose, and lighting. To understand how visual sensory neurons enable robust perception, it is crucial to characterize their selectivity to such physically…