相关论文: Active Stereo Without Pattern Projector

We present an active physical implementation of the recently introduced plasmon injection loss compensation scheme for Pendry's non-ideal negative index flat lens in the presence of realistic material losses and signal-dependent noise. In…

As object detectors rapidly improve, attention has expanded past image-only networks to include a range of 3D and multimodal frameworks, especially ones that incorporate LiDAR. However, due to cost, logistics, and even some safety…

The photometric stereo (PS) problem consists in reconstructing the 3D-surface of an object, thanks to a set of photographs taken under different lighting directions. In this paper, we propose a multi-scale architecture for PS which,…

Stereo foundation models achieve strong zero-shot generalization but remain computationally prohibitive for real-time applications. Efficient stereo architectures, on the other hand, sacrifice robustness for speed and require costly…

With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress. However, it remains a great challenge to accurately extract disparities from real-world image pairs taken by…

Stereo cameras are a popular choice for obstacle avoidance for outdoor lighweight, low-cost robotics applications. However, they are unable to sense thin and reflective objects well. Currently, many algorithms are tuned to perform well on…

In this paper, we propose a novel projector-camera system for practical and low-cost acquisition of a dense object 3D model with the spectral reflectance property. In our system, we use a standard RGB camera and leverage an off-the-shelf…

We introduce a novel method to perform linear optical random projections without the need for holography. Our method consists of a computationally trivial combination of multiple intensity measurements to mitigate the information loss…

Real time outdoor navigation in highly dynamic environments is an crucial problem. The recent literature on real time static SLAM don't scale up to dynamic outdoor environments. Most of these methods assume moving objects as outliers or…

Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. Among the existing techniques, stereo matching remains one of the…

We propose EventHub, a novel framework for training deep-event stereo networks without ground truth annotations from costly active sensors, relying instead on standard color images. From these images, we derive either proxy annotations and…

Existing permanental processes often impose constraints on kernel types or stationarity, limiting the model's expressiveness. To overcome these limitations, we propose a novel approach utilizing the sparse spectral representation of…

In this paper we introduce a novel platform for dense 3D modelling. This platform is an active image acquisition setup assisted with a set of light sources and a distance sensor. The hardware setup is designed for being mounted on a mobile…

Real-time Stereo Matching is a cornerstone algorithm for many Extended Reality (XR) applications, such as indoor 3D understanding, video pass-through, and mixed-reality games. Despite significant advancements in deep stereo methods,…

This paper introduces a novel deep framework for dense 3D reconstruction from multiple image frames, leveraging a sparse set of depth measurements gathered jointly with image acquisition. Given a deep multi-view stereo network, our…

Random projection is often used to project higher-dimensional vectors onto a lower-dimensional space, while approximately preserving their pairwise distances. It has emerged as a powerful tool in various data processing tasks and has…

We introduce the Deep Spectral Prior (DSP), a new framework for unsupervised image reconstruction that operates entirely in the complex frequency domain. Unlike the Deep Image Prior (DIP), which optimises pixel-level errors and is highly…

Stereo matching is one of the most popular techniques to estimate dense depth maps by finding the disparity between matching pixels on two, synchronized and rectified images. Alongside with the development of more accurate algorithms, the…

Depth perception is pivotal in many fields, such as robotics and autonomous driving, to name a few. Consequently, depth sensors such as LiDARs rapidly spread in many applications. The 3D point clouds generated by these sensors must often be…

Although depth extraction with passive sensors has seen remarkable improvement with deep learning, these approaches may fail to obtain correct depth if they are exposed to environments not observed during training. Online adaptation, where…