Related papers: A Multilevel Sampling Method for Detecting Sources…
The denoising process of diffusion models can be interpreted as an approximate projection of noisy samples onto the data manifold. Moreover, the noise level in these samples approximates their distance to the underlying manifold. Building…
Sound Source Localization (SSL) are used to estimate the position of sound sources. Various methods have been used for detecting sound and its localization. This paper presents a system for stationary sound source localization by cubical…
Generating realistic human 3D reconstructions using image or video data is essential for various communication and entertainment applications. While existing methods achieved impressive results for body and facial regions, realistic hair…
We consider the inverse problem of determining the geometry of penetrable objects from scattering data generated by one incident wave at a fixed frequency. We first study an orthogonality sampling type method which is fast, simple to…
We study the problem of single-image 3D object reconstruction. Recent works have diverged into two directions: regression-based modeling and generative modeling. Regression methods efficiently infer visible surfaces, but struggle with…
We present a method for detection and reconstruction of the gravitational-wave (GW) transients with the networks of advanced detectors. Originally designed to search for transients with the initial GW detectors, it uses significantly…
In this paper we propose a novel approach aimed at recovering the 3D position of an UUV from UAV imagery in shallow-water environments. Through combination of UAV and UUV measurements, we show that our method can be utilized as an accurate…
Source extension is a reformulation of inverse problems in wave propagation, that at least in some cases leads to computationally tractable iterative solution methods. The core subproblem in all source extension methods is the solution of a…
The efficient fusion of depth maps is a key part of most state-of-the-art 3D reconstruction methods. Besides requiring high accuracy, these depth fusion methods need to be scalable and real-time capable. To this end, we present a novel…
In autonomous driving, mapping is critical for motion planning but remains an under-utilized resource for perception tasks such as 3D object detection. Maps can provide robust structural priors of the static environment, helping resolve…
Existing methods utilizing spatial information for sound source separation require prior knowledge of the direction of arrival (DOA) of the source or utilize estimated but imprecise localization results, which impairs the separation…
We present an approach to inform the reconstruction of a surface from a point scan through topological priors. The reconstruction is based on basis functions which are optimized to provide a good fit to the point scan while satisfying…
Optical vibration sensing enables recovering the scene sound directly from the surface vibration of nearby objects, turning everyday objects into ``visual microphones''. However, most prior methods had focused on capturing the vibrations of…
Novel view synthesis from images, for example, with 3D Gaussian splatting, has made great progress. Rendering fidelity and speed are now ready even for demanding virtual reality applications. However, the problem of assisting humans in…
Automatic reconstruction of 3D models from images using multi-view Structure-from-Motion methods has been one of the most fruitful outcomes of computer vision. These advances combined with the growing popularity of Micro Aerial Vehicles as…
Sound sources localization using multichannel signal processing has been a subject of active research for decades. In recent years, the use of deep learning in audio signal processing has allowed to drastically improve performances for…
Objective: The computation of anatomical information and laparoscope position is a fundamental block of surgical navigation in Minimally Invasive Surgery (MIS). Recovering a dense 3D structure of surgical scene using visual cues remains a…
Edges are one of the most basic parametric primitives to describe structural information in 3D. In this paper, we study parametric 3D edge reconstruction from calibrated multi-view images. Previous methods usually reconstruct a 3D edge…
We introduce a method to classify imagery using a convo- lutional neural network (CNN) on multi-view image pro- jections. The power of our method comes from using pro- jections of multiple images at multiple depth planes near the…
We develop three inverse elastic scattering schemes for locating multiple small, extended and multiscale rigid bodies, respectively. There are some salient and promising features of the proposed methods. The cores of those schemes are…