Zobrazeno 1 - 10
of 502
pro vyhledávání: '"Davison Andrew P"'
Visual sensors are not only becoming better at capturing high-quality images but also they have steadily increased their capabilities in processing data on their own on-chip. Yet the majority of VO pipelines rely on the transmission and processing of
Externí odkaz:
http://arxiv.org/abs/2406.09726
Autor:
Dexheimer, Eric, Davison, Andrew J.
We present COMO, a real-time monocular mapping and odometry system that encodes dense geometry via a compact set of 3D anchor points. Decoding anchor point projections into dense geometry via per-keyframe depth covariance functions guarantees that de
Externí odkaz:
http://arxiv.org/abs/2404.03531
Camera rotation estimation from a single image is a challenging task, often requiring depth data and/or camera intrinsics, which are generally not available for in-the-wild videos. Although external sensors such as inertial measurement units (IMUs) c
Externí odkaz:
http://arxiv.org/abs/2403.15583
Autor:
Bae, Gwangbin, Davison, Andrew J.
Despite the growing demand for accurate surface normal estimation models, existing methods use general-purpose dense prediction models, adopting the same inductive biases as other tasks. In this paper, we discuss the inductive biases needed for surfa
Externí odkaz:
http://arxiv.org/abs/2403.00712
We introduce EscherNet, a multi-view conditioned diffusion model for view synthesis. EscherNet learns implicit and generative 3D representations coupled with a specialised camera positional encoding, allowing precise and continuous relative control o
Externí odkaz:
http://arxiv.org/abs/2402.03908
Publikováno v:
IEEE Robotics and Automation Letters, vol. 9, no. 3, pp. 2136-2143, March 2024
We present a novel scalable, fully distributed, and online method for simultaneous localisation and extrinsic calibration for multi-robot setups. Individual a priori unknown robot poses are probabilistically inferred as robots sense each other while
Externí odkaz:
http://arxiv.org/abs/2401.15036
Accurate 3D object pose estimation is key to enabling many robotic applications that involve challenging object interactions. In this work, we show that the density field created by a state-of-the-art efficient radiance field reconstruction method is
Externí odkaz:
http://arxiv.org/abs/2401.02357
We present the first application of 3D Gaussian Splatting in monocular SLAM, the most fundamental but the hardest setup for Visual SLAM. Our method, which runs live at 3fps, utilises Gaussians as the only 3D representation, unifying the required repr
Externí odkaz:
http://arxiv.org/abs/2312.06741
Joint camera pose and dense geometry estimation from a set of images or a monocular video remains a challenging problem due to its computational complexity and inherent visual ambiguities. Most dense incremental reconstruction systems operate directl
Externí odkaz:
http://arxiv.org/abs/2312.05889
We propose an approach to do learning in Gaussian factor graphs. We treat all relevant quantities (inputs, outputs, parameters, latents) as random variables in a graphical model, and view both training and prediction as inference problems with differ
Externí odkaz:
http://arxiv.org/abs/2311.14649