Related papers: Direct volumetric reconstruction for highly compre…
Three-dimensional reconstruction is a fundamental problem in robotics perception. We examine the problem of active view selection to perform 3D Gaussian Splatting reconstructions with as few input images as possible. Although 3D Gaussian…
The characterization of nanostructured surfaces with sensitivity in the sub-nm range is of high importance for the development of current and next generation integrated electronic circuits. Modern transistor architectures for e.g. FinFETs…
Ghost imaging leverages a single-pixel detector with no spatial resolution to acquire object echo intensity signals, which are correlated with illumination patterns to reconstruct an image. This architecture inherently mitigates scattering…
Neural radiance fields (NeRFs) are able to synthesize realistic novel views from multi-view images captured from distinct positions and perspectives. In NeRF's rendering pipeline, neural networks are used to represent a scene independently…
We present a lightweight solution for estimating spatially-coherent indoor lighting from a single RGB image. Previous methods for estimating illumination using volumetric representations have overlooked the sparse distribution of light…
We extend the recently proposed sparse voxel rasterization paradigm to the task of high-fidelity surface reconstruction by integrating Signed Distance Function (SDF), named SVRecon. Unlike 3D Gaussians, sparse voxels are spatially…
Quarter sampling is a novel sensor design that allows for an acquisition of higher resolution images without increasing the number of pixels. When being used for video data, one out of four pixels is measured in each frame. Effectively,…
Measurements from the Event Horizon Telescope enabled the visualization of light emission around a black hole for the first time. So far, these measurements have been used to recover a 2D image under the assumption that the emission field…
GeRaF is the first method to use neural implicit learning for near-range 3D geometry reconstruction from radio frequency (RF) signals. Unlike RGB or LiDAR-based methods, RF sensing can see through occlusion but suffers from low resolution…
Fluorescence microscopy (FM) imaging is a fundamental technique for observing live cell division, one of the most essential processes in the cycle of life and death. Observing 3D live cells requires scanning through the cell volume while…
Time-resolved fluorescence imaging is a key tool in biomedical applications, as it allows to non-invasively obtain functional and structural information. However, the big amount of collected data introduces challenges in both acquisition…
We present a deep learning driven computational approach to overcome the limitations of self-interference digital holography that imposed by inferior axial imaging performances. We demonstrate a 3D deep neural network model can…
X-ray imaging is a prevalent technique for non-invasively visualizing the interior of the human body and opaque instruments. In most commercial x-ray modalities, an image is formed by measuring the x-rays that pass through the object of…
Conventional tomographic reconstruction algorithms assume that one has obtained pure projection images, involving no within-specimen diffraction effects nor multiple scattering. Advances in x-ray nanotomography are leading towards the…
Recently, 3D Gaussian Splatting (3DGS) has enabled photorealistic view synthesis at high inference speeds. However, its splatting-based rendering model makes several approximations to the rendering equation, reducing physical accuracy. We…
We present a deep learning approach to reconstruct scene appearance from unstructured images captured under collocated point lighting. At the heart of Deep Reflectance Volumes is a novel volumetric scene representation consisting of…
By means of numerical simulations, we demonstrate the innovative use of computational ghost imaging in transmission electron microscopy to retrieve images with a resolution that overcomes the limitations imposed by coherent aberrations. The…
We introduce a structured illumination technique for dark-field x-ray microscopy optimized for three-dimensional imaging of ordered materials at sub-micrometer length scales. Our method utilizes a coded aperture to spatially modulate the…
The success of the Neural Radiance Fields (NeRF) in novel view synthesis has inspired researchers to propose neural implicit scene reconstruction. However, most existing neural implicit reconstruction methods optimize per-scene parameters…
Reconstructing three-dimensional (3D) scenes with semantic understanding is vital in many robotic applications. Robots need to identify which objects, along with their positions and shapes, to manipulate them precisely with given tasks.…