Related papers: MuS-Polar3D: A Benchmark Dataset for Computational…
Simultaneous localization and mapping is essential for position tracking and scene understanding. 3D Gaussian-based map representations enable photorealistic reconstruction and real-time rendering of scenes using multiple posed cameras. We…
MaskedFusion is a framework to estimate the 6D pose of objects using RGB-D data, with an architecture that leverages multiple sub-tasks in a pipeline to achieve accurate 6D poses. 6D pose estimation is an open challenge due to complex world…
Water ice has a strong spectral feature at a wavelength of approximately $3~\mu$m, which plays a vital role in our understanding of the icy universe. In this study, we investigate the scattering polarization of this water-ice feature. The…
Accurate and consistent 3D tracking from multiple cameras is a key component in a vision-based autonomous driving system. It involves modeling 3D dynamic objects in complex scenes across multiple cameras. This problem is inherently…
Commercial off the shelf (COTS) 3D scanners are capable of generating point clouds covering visible portions of a face with sub-millimeter accuracy at close range, but lack the coverage and specialized anatomic registration provided by more…
Wavefront shaping has revolutionized imaging deep in scattering media, being able to spatially and temporally refocus light through or inside the medium. However, wavefront shaping is not compatible yet with polarization-resolved microscopy…
Three-dimensional phase contrast imaging of multiply-scattering samples in X-ray and electron microscopy is extremely challenging, due to small numerical apertures, the unavailability of wavefront shaping optics, and the highly nonlinear…
The recent paradigm shift in 3D vision led to the rise of foundation models with remarkable capabilities in 3D perception from uncalibrated images. However, extending these models to large-scale RGB stream 3D reconstruction remains…
A technique based on speckle contrast measurement is proposed and demonstrated to track the polarization rotation of an optical beam behind a scattering layer. It is shown that with the help of a reference speckle pattern with a known…
We present a deep neural network based method for the retrieval of watermarks from images of 3D printed objects. To deal with the variability of all possible 3D printing and image acquisition settings we train the network with synthetic…
Real-time satellite imaging has a central role in monitoring, detecting and estimating the intensity of key natural phenomena such as floods, earthquakes, etc. One important constraint of satellite imaging is the trade-off between…
Analysis of compressible turbulent flows is essential for applications related to propulsion, energy generation, and the environment. Here, we present BLASTNet 2.0, a 2.2 TB network-of-datasets containing 744 full-domain samples from 34…
We present 3D Spatial MultiModal Memory (M3), a multimodal memory system designed to retain information about medium-sized static scenes through video sources for visual perception. By integrating 3D Gaussian Splatting techniques with…
Light-matter interactions within indoor environments are significantly depolarizing. Nonetheless, the relatively small polarization attributes are informative. To make use of this information, polarized-BRDF (pBRDF) models for common indoor…
Future telescopes will characterize rocky exoplanets in reflected light, revealing their albedo, which depends on surface, cloud, and atmospheric properties. Identifying these features is crucial for assessing habitability. We present…
Optical metasurfaces have been recently explored as ultrathin analog image differentiators. By tailoring the momentum transfer function, they can perform efficient Fourier-filtering - and thus potentially any linear mathematical operation -…
Multiple scattering of waves in disordered media is a nightmare whether it be for detection or imaging purposes. The best approach so far to get rid of multiple scattering is optical coherence tomography. It basically combines confocal…
Reliable three-dimensional human pose estimation (3D HPE) remains challenging due to the differences in viewpoints, environments, and camera conventions among datasets. As a result, methods that achieve near-optimal in-dataset accuracy…
Polarized dust emission is widely used to trace the plane-of-the-sky (POS) component of interstellar magnetic fields in two dimensions. Its potential to access three-dimensional magnetic fields, including the inclination angle of the…
In this work, we propose a novel method for the detailed reconstruction of transparent objects by exploiting polarimetric cues. Most of the existing methods usually lack sufficient constraints and suffer from the over-smooth problem. Hence,…