We obtain the exact value of the Hausdorff dimension of the set of coefficients of Gauss sums which for a given $alpha in (1/2,1)$ achieve the order at least $N^{alpha}$ for infinitely many sum lengths $N$. For Weyl sums with polynomials of degree $d
ge 3$ we obtain a new upper bound on the Hausdorff dimension of the set of polynomial coefficients corresponding to large values of Weyl sums. Our methods also work for monomial sums, match the previously known lower bounds, just giving exact value for the corresponding Hausdorff dimension when $alpha$ is close to $1$. We also obtain a nearly tight bound in a similar question with arbitrary integer sequences of polynomial growth.
We obtain new estimates on the maximal operator applied to the Weyl sums. We also consider the quadratic case (that is, Gauss sums) in more details. In wide ranges of parameters our estimates are optimal and match lower bounds. Our approach is based
on a combination of ideas of Baker (2021) and Chen and Shparlinski (2020).
Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds. Despite a plethora of learning-based 2D or 3D local feature descriptors and detectors having been proposed, the derivat
ion of a shared descriptor and joint keypoint detector that directly matches pixels and points remains under-explored by the community. This work takes the initiative to establish fine-grained correspondences between 2D images and 3D point clouds. In order to directly match pixels and points, a dual fully convolutional framework is presented that maps 2D and 3D inputs into a shared latent representation space to simultaneously describe and detect keypoints. Furthermore, an ultra-wide reception mechanism in combination with a novel loss function are designed to mitigate the intrinsic information variations between pixel and point local regions. Extensive experimental results demonstrate that our framework shows competitive performance in fine-grained matching between images and point clouds and achieves state-of-the-art results for the task of indoor visual localization. Our source code will be available at [no-name-for-blind-review].
We prove that there exist positive constants $C$ and $c$ such that for any integer $d ge 2$ the set of ${mathbf x}in [0,1)^d$ satisfying $$ cN^{1/2}le left|sum^N_{n=1}expleft (2 pi i left (x_1n+ldots+x_d n^dright)right) right|le C N^{1/2}$$ for infin
itely many natural numbers $N$ is of full Lebesque measure. This substantially improves the previous results where similar sets have been measured in terms of the Hausdorff dimension. We also obtain similar bounds for exponential sums with monomials $xn^d$ when $d eq 4$. Finally, we obtain lower bounds for the Hausdorff dimension of large values of general exponential polynomials.
Deep learning based localization and mapping has recently attracted significant attention. Instead of creating hand-designed algorithms through exploitation of physical models or geometric theories, deep learning based solutions provide an alternativ
e to solve the problem in a data-driven way. Benefiting from ever-increasing volumes of data and computational power, these methods are fast evolving into a new area that offers accurate and robust systems to track motion and estimate scenes and their structure for real-world applications. In this work, we provide a comprehensive survey, and propose a new taxonomy for localization and mapping using deep learning. We also discuss the limitations of current models, and indicate possible future directions. A wide range of topics are covered, from learning odometry estimation, mapping, to global localization and simultaneous localization and mapping (SLAM). We revisit the problem of perceiving self-motion and scene understanding with on-board sensors, and show how to solve it by integrating these modules into a prospective spatial machine intelligence system (SMIS). It is our hope that this work can connect emerging works from robotics, computer vision and machine learning communities, and serve as a guide for future researchers to apply deep learning to tackle localization and mapping problems.
S. Baker (2019), B. Barany and A. K{a}enm{a}ki (2019) independently showed that there exist iterated function systems without exact overlaps and there are super-exponentially close cylinders at all small levels. We adapt the method of S. Baker and ob
tain further examples of this type. We prove that for any algebraic number $betage 2$ there exist real numbers $s, t$ such that the iterated function system $$ left {frac{x}{beta}, frac{x+1}{beta}, frac{x+s}{beta}, frac{x+t}{beta}right } $$ satisfies the above property.
We prove that the Hausdorff dimension of the set $mathbf{x}in [0,1)^d$, such that $$ left|sum_{n=1}^N expleft(2 pi ileft(x_1n+ldots+x_d n^dright)right) right|ge c N^{1/2} $$ holds for infinitely many natural numbers $N$, is at least $d-1/2d$ for $d g
e 3$ and at least $3/2$ for $d=2$, where $c$ is a constant depending only on $d$. This improves the previous lower bound of the first and third authors for $dge 3$. We also obtain similar bounds for the Hausdorff dimension of the set of large sums with monomials $xn^d$.
Recent learning-based approaches have achieved impressive results in the field of single-shot camera localization. However, how best to fuse multiple modalities (e.g., image and depth) and to deal with degraded or missing input are less well studied.
In particular, we note that previous approaches towards deep fusion do not perform significantly better than models employing a single modality. We conjecture that this is because of the naive approaches to feature space fusion through summation or concatenation which do not take into account the different strengths of each modality. To address this, we propose an end-to-end framework, termed VMLoc, to fuse different sensor inputs into a common latent space through a variational Product-of-Experts (PoE) followed by attention-based fusion. Unlike previous multimodal variational works directly adapting the objective function of vanilla variational auto-encoder, we show how camera localization can be accurately estimated through an unbiased objective function based on importance weighting. Our model is extensively evaluated on RGB-D datasets and the results prove the efficacy of our model. The source code is available at https://github.com/Zalex97/VMLoc.
Modern inertial measurements units (IMUs) are small, cheap, energy efficient, and widely employed in smart devices and mobile robots. Exploiting inertial data for accurate and reliable pedestrian navigation supports is a key component for emerging In
ternet-of-Things applications and services. Recently, there has been a growing interest in applying deep neural networks (DNNs) to motion sensing and location estimation. However, the lack of sufficient labelled data for training and evaluating architecture benchmarks has limited the adoption of DNNs in IMU-based tasks. In this paper, we present and release the Oxford Inertial Odometry Dataset (OxIOD), a first-of-its-kind public dataset for deep learning based inertial navigation research, with fine-grained ground-truth on all sequences. Furthermore, to enable more efficient inference at the edge, we propose a novel lightweight framework to learn and reconstruct pedestrian trajectories from raw IMU data. Extensive experiments show the effectiveness of our dataset and methods in achieving accurate data-driven pedestrian inertial navigation on resource-constrained devices.
Autonomous vehicles and mobile robotic systems are typically equipped with multiple sensors to provide redundancy. By integrating the observations from different sensors, these mobile agents are able to perceive the environment and estimate system st
ates, e.g. locations and orientations. Although deep learning approaches for multimodal odometry estimation and localization have gained traction, they rarely focus on the issue of robust sensor fusion - a necessary consideration to deal with noisy or incomplete sensor observations in the real world. Moreover, current deep odometry models also suffer from a lack of interpretability. To this extent, we propose SelectFusion, an end-to-end selective sensor fusion module which can be applied to useful pairs of sensor modalities such as monocular images and inertial measurements, depth images and LIDAR point clouds. During prediction, the network is able to assess the reliability of the latent features from different sensor modalities and estimate both trajectory at scale and global pose. In particular, we propose two fusion modules based on different attention strategies: deterministic soft fusion and stochastic hard fusion, and we offer a comprehensive study of the new strategies compared to trivial direct fusion. We evaluate all fusion strategies in both ideal conditions and on progressively degraded datasets that present occlusions, noisy and missing data and time misalignment between sensors, and we investigate the effectiveness of the different fusion strategies in attending the most reliable features, which in itself, provides insights into the operation of the various models.
