Related papers: VioLA: Aligning Videos to 2D LiDAR Scans
This paper proposes an efficient and probabilistic adaptive voxel mapping method for LiDAR odometry. The map is a collection of voxels; each contains one plane (or edge) feature that enables the probabilistic representation of the…
The ability to identify the static background in videos captured by a moving camera is an important pre-requisite for many video applications (e.g. video stabilization, stitching, and segmentation). Existing methods usually face…
Localization is an essential technique in mobile robotics. In a complex environment, it is necessary to fuse different localization modules to obtain more robust results, in which the error model plays a paramount role. However,…
Existing visual localization methods are typically either 2D image-based, which are easy to build and maintain but limited in effective geometric reasoning, or 3D structure-based, which achieve high accuracy but require a centralized…
Scene understanding and reasoning has been a fundamental problem in 3D computer vision, requiring models to identify objects, their properties, and spatial or comparative relationships among the objects. Existing approaches enable this by…
Today's autonomous vehicles rely on a multitude of sensors to perceive their environment. To improve the perception or create redundancy, the sensor's alignment relative to each other must be known. With Multi-LiCa, we present a novel…
Although large-scale video-language pre-training models, which usually build a global alignment between the video and the text, have achieved remarkable progress on various downstream tasks, the idea of adopting fine-grained information…
This technical report introduces CyberLoc, an image-based visual localization pipeline for robust and accurate long-term pose estimation under challenging conditions. The proposed method comprises four modules connected in a sequence.…
The visual camera is an attractive device in beyond visual line of sight (B-VLOS) drone operation, since they are low in size, weight, power, and cost, and can provide redundant modality to GPS failures. However, state-of-the-art visual…
As the number of installed cameras grows, so do the compute resources required to process and analyze all the images captured by these cameras. Video analytics enables new use cases, such as smart cities or autonomous driving. At the same…
This paper presents a novel system designed for 3D mapping and visual relocalization using 3D Gaussian Splatting. Our proposed method uses LiDAR and camera data to create accurate and visually plausible representations of the environment.…
We consider the problem of enriching current object detection systems with veridical object sizes and relative depth estimates from a single image. There are several technical challenges to this, such as occlusions, lack of calibration data…
This paper is about 3D pose estimation on LiDAR scans with extremely minimal storage requirements to enable scalable mapping and localisation. We achieve this by clustering all points of segmented scans into semantic objects and…
Low-light videos often exhibit spatiotemporal incoherent noise, leading to poor visibility and compromised performance across various computer vision applications. One significant challenge in enhancing such content using modern…
The problem of segmenting a given image into coherent regions is important in Computer Vision and many industrial applications require segmenting a known object into its components. Examples include identifying individual parts of a…
Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. The key challenge preventing the deployment of these 3D scene learners on large-scale video data is their…
Robust and accurate, map-based localization is crucial for autonomous mobile systems. In this paper, we exploit range images generated from 3D LiDAR scans to address the problem of localizing mobile robots or autonomous cars in a map of a…
Constructing precise global maps is a key task in robotics and is required for localization, surveying, monitoring, or constructing digital twins. To build accurate maps, data from mobile 3D LiDAR sensors is often used. Mapping requires…
Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled examples. This work…
Accurate and robust visual localization under a wide range of viewing condition variations including season and illumination changes, as well as weather and day-night variations, is the key component for many computer vision and robotics…