Related papers: NeRF-VO: Real-Time Sparse Visual Odometry with Neu…

Considering the problem of novel view synthesis (NVS) from only a set of 2D images, we simplify the training process of Neural Radiance Field (NeRF) on forward-facing scenes by removing the requirement of known or pre-computed camera…

Dense visual odometry (VO), which provides pose estimation and dense 3D reconstruction, serves as the cornerstone for applications ranging from robotics to augmented reality. Recently, feed-forward models have demonstrated remarkable…

Monocular visual odometry (VO) is a fundamental computer vision problem with applications in autonomous navigation, augmented reality and more. While deep learning-based methods have recently shown superior accuracy compared to traditional…

Virtual Reality (VR) is becoming ubiquitous with the rise of consumer displays and commercial VR platforms. Such displays require low latency and high quality rendering of synthetic imagery with reduced compute overheads. Recent advances in…

Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution, offering the potential to handle state estimation tasks involving motion blur and high…

In this work we present a monocular visual odometry (VO) algorithm which leverages geometry-based methods and deep learning. Most existing VO/SLAM systems with superior performance are based on geometry and have to be carefully designed for…

Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs. While traditional VO methods excel in some conditions, they struggle with challenges like…

A prior map serves as a foundational reference for localization in context-aware applications such as augmented reality (AR). Providing valuable contextual information about the environment, the prior map is a vital tool for mitigating…

Visual odometry (VO) aims to estimate camera poses from visual inputs -- a fundamental building block for many applications such as VR/AR and robotics. This work focuses on monocular RGB VO where the input is a monocular RGB video without…

Neural radiance fields (NeRF) have achieved impressive performances in view synthesis by encoding neural representations of a scene. However, NeRFs require hundreds of images per scene to synthesize photo-realistic novel views. Training…

Event cameras offer the exciting possibility of tracking the camera's pose during high-speed motion and in adverse lighting conditions. Despite this promise, existing event-based monocular visual odometry (VO) approaches demonstrate limited…

In modern dense 3D reconstruction, feed-forward systems (e.g., VGGT, pi3) focus on end-to-end matching and geometry prediction but do not explicitly output the novel view synthesis (NVS). Neural rendering-based approaches offer…

Neural Radiance Fields (NeRF) enable 3D scene reconstruction from 2D images and camera poses for Novel View Synthesis (NVS). Although NeRF can produce photorealistic results, it often suffers from overfitting to training views, leading to…

Learning accurate scene reconstruction without pose priors in neural radiance fields is challenging due to inherent geometric ambiguity. Recent development either relies on correspondence priors for regularization or uses off-the-shelf flow…

Visual Odometry (VO) plays a pivotal role in autonomous systems, with a principal challenge being the lack of depth information in camera images. This paper introduces OCC-VO, a novel framework that capitalizes on recent advances in deep…

Due to the ability to synthesize high-quality novel views, Neural Radiance Fields (NeRF) have been recently exploited to improve visual localization in a known environment. However, the existing methods mostly utilize NeRFs for data…

Monocular omnidirectional visual odometry (OVO) systems leverage 360-degree cameras to overcome field-of-view limitations of perspective VO systems. However, existing methods, reliant on handcrafted features or photometric objectives, often…

Neural Radiance Field (NeRF) and its variants have exhibited great success on representing 3D scenes and synthesizing photo-realistic novel views. However, they are generally based on the pinhole camera model and assume all-in-focus inputs.…

The monocular visual-inertial odometry (VIO) based on the direct method can leverage all available pixels in the image to simultaneously estimate the camera motion and reconstruct the denser map of the scene in real time. However, the…

NeRF aims to learn a continuous neural scene representation by using a finite set of input images taken from various viewpoints. A well-known limitation of NeRF methods is their reliance on data: the fewer the viewpoints, the higher the…