Query Point Research Articles

Exact and efficient search-based wall distance algorithm for partitioned unstructured grids

In this paper, we develop a novel search-based wall distance calculation algorithm. The algorithm is highly efficient and satisfies the crucial requirement of exactness in wall distance calculations, taking into account the full geometry of the discretized surface. Unlike conventional search-based algorithms that use element-wise bounding boxes or auxiliary grids, the developed algorithm employs only a set of zero-dimensional reference points representing the elements of the discretized surface. Reference points can be chosen as the centers of faces, the centers of edges, or the vertices. The conservative relation between the approximate distance using one of these references and the exact distance is established, allowing for the efficient extraction of element candidates using only low-level information. The algorithm does not require complex pre-processing of the surface or any information about the query points, ensuring high software modularity. An intuitive load balancing procedure is also proposed to address the load imbalance arising from partitioning-based parallelization. Numerical test demonstrates that the developed algorithm shows three orders of magnitude speed-up compared to exhaustive search and one to two orders of magnitude speed-up compared to other search-based algorithms. It also shows high parallel scalability on partitioned meshes, indicating its feasibility for large-scale problems.

Instability results for cosine-dissimilarity-based nearest neighbor search on high dimensional Gaussian data

Because many dissimilarity functions behave differently in low versus high-dimensional spaces, the behavior of high-dimensional nearest neighbor search has been studied extensively. One line of research involves the characterization of nearest neighbor queries as unstable if their query points have nearly identical dissimilarity with most points in the dataset. This research has shown that, for various data distributions and dissimilarity functions, the probability of query instability approaches one. Previous work in Information Processing Letters by C. Giannella in 2021 explicated this phenomenon for centered Gaussian data and Euclidean distance. This paper addresses the problem of characterizing query instability behavior over centered Gaussian data and a fundamentally different dissimilarity function, cosine dissimilarity. Conditions are provided on the covariance matrices and dataset size function guaranteeing that the probability of query instability goes to one. Furthermore, conditions are provided under which the instability probability is bounded away from one.

A multi-average based pseudo nearest neighbor classifier

Conventional k nearest neighbor (KNN) rule is a simple yet effective method for classification, but its classification performance is easily degraded in the case of small size training samples with existing outliers. To address this issue, A multi-average based pseudo nearest neighbor classifier (MAPNN) rule is proposed. In the proposed MAPNN rule, k ( k − 1 ) / 2 ( k > 1) local mean vectors of each class are obtained by taking the average of two points randomly from k nearest neighbors in every category, and then k pseudo nearest neighbors are chosen from k ( k − 1 ) / 2 local mean neighbors of every class to determine the category of a query point. The selected k pseudo nearest neighbors can reduce the negative impact of outliers in some degree. Extensive experiments are carried out on twenty-one numerical real data sets and four artificial data sets by comparing MAPNN to other five KNN-based methods. The experimental results demonstrate that the proposed MAPNN is effective for classification task and achieves better classification results in the small-size samples cases comparing to five relative KNN-based classifiers.

Rethinking Multilingual Scene Text Spotting: A Novel Benchmark and a Character-Level Feature Based Approach

End-to-end multilingual scene text spotting aims to integrate scene text detection and recognition into a unified framework. Actually, the accuracy of text recognition largely depends on the accuracy of text detection. Due to the lackage of benchmarks with adequate and high-quality character-level annotations for multilingual scene text spotting, most of the existing methods train on the benchmarks only with word-level annotations. However, the performance of multilingual scene text spotting are not that satisfied training on the existing benchmarks, especially for those images with special layout or words out of vocabulary. In this paper, we proposed a simple YOLO-like baseline named CMSTR for character-level multilingual scene text spotting simultaneously and efficiently. Technically, for each text instance, we represent the character sequence as ordered points and model them with learnable explicit point queries. After passing a single decoder, the point queries have encoded requisite text semantics and locations, thus can be further decoded to the center line, boundary, script, and confidence of text via very simple prediction heads in parallel. Furthermore, we show the surprisingly good extensibility of our method, in terms of character class, language type, and task. On the one hand, DeepSolo not only performs well in English scenes but also masters the Chinese transcription with complex font structure and a thousand-level character classes. On the other hand, based on the extensibility of DeepSolo, we launch DeepSolo++ for multilingual text spotting, making a further step to let Transformer decoder with explicit points solo for multilingual text detection, recognition, and script identification all at once.

DPGS: Cross-cooperation guided dynamic points generation for scene text spotting

End-to-end text spotting aims to combine scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. While polygon or segmentation-based methods eliminate heuristic post-processing, they still face challenges such as background noise and high computational burden. In this study, we introduce DPGS, a coarse-to-fine learning framework that lets Dynamic Points Generation for text Spotting. DPGS simultaneously learns character representations for both detection and recognition tasks. Specifically, for each text instance, we represent the character sequence as ordered points and model them with learnable point queries. This approach progressively selects appropriate key points covering character and leverages group attention to associate similar information from different positions, improving detection accuracy. After passing through a single decoder, the point queries encode text semantics and locations, facilitating decoding to central line, boundary, script, and confidence of text through simple prediction heads. Additionally, we introduce an adaptive cooperative criterion to combine more useful feature knowledge, enhancing training efficiency. Extensive experiments show the superiority of our DPGS when handling scene text detection and recognition tasks. Compared to their respective top-1 methods, DPGS has significantly improved the average recognition accuracy by 3.7%, 1.9%, and 0.7% on the Total-Text, ICDAR15, and CTW1500 datasets, respectively.

RobotSDF: Implicit Morphology Modeling for the Robotic Arm.

The expression of robot arm morphology is a critical foundation for achieving effective motion planning and collision avoidance in robotic systems. Traditional geometry-based approaches usually suffer from the contradiction between the high demand for computing resources for fine expression and the insufficient detail expression caused by the pursuit of efficiency. The signed distance function addresses these drawbacks due to its ability to handle complex and arbitrary shapes and lower computational requirements. However, conventional robotic morphology methods based on the signed distance function often face challenges when the robot moves dynamically, since robots with different postures are modeled as independent individuals but the postures of robots are infinite. In this paper, we introduce RobotSDF, an implicit morphology modeling approach that can express the robot shape of arbitrary posture precisely. Instead of depicting a whole model of the robot arm, RobotSDF models the robot morphology as integrated implicit joint models driven by joint configurations. In this approach, the dynamic shape change process of the robot is converted into the coordinate transformations of query points within each joint's coordinate system. Experimental results with the Elfin robot demonstrate that RobotSDF can accurately depict robot shapes across different postures up to the millimeter level, which exhibits 38.65% and 66.24% improvement over the Neural-JSDF and configuration space distance field algorithms, respectively, in representing robot morphology. We further verified the efficiency of RobotSDF through collision avoidance in both simulation and actual human-robot collaboration experiments.

Implicit Swept Volume SDF: Enabling Continuous Collision-Free Trajectory Generation for Arbitrary Shapes

In the field of trajectory generation for objects, ensuring continuous collision-free motion remains a huge challenge, especially for non-convex geometries and complex environments. Previous methods either oversimplify object shapes, which results in a sacrifice of feasible space or rely on discrete sampling, which suffers from the "tunnel effect". To address these limitations, we propose a novel hierarchical trajectory generation pipeline, which utilizes the Swept Volume Signed Distance Field (SVSDF) to guide trajectory optimization for Continuous Collision Avoidance (CCA). Our interdisciplinary approach, blending techniques from graphics and robotics, exhibits outstanding effectiveness in solving this problem. We formulate the computation of the SVSDF as a Generalized Semi-Infinite Programming model, and we solve for the numerical solutions at query points implicitly, thereby eliminating the need for explicit reconstruction of the surface. Our algorithm has been validated in a variety of complex scenarios and applies to robots of various dynamics, including both rigid and deformable shapes. It demonstrates exceptional universality and superior CCA performance compared to typical algorithms. The code will be released at https://github.com/ZJU-FAST-Lab/Implicit-SVSDF-Planner for the benefit of the community.

Voronoi Diagram-based USBL Outlier Rejection for AUV Localization

USBL systems are essential for providing accurate positions of autonomous underwater vehicles (AUVs). On the other hand, the accuracy can be degraded by outliers because of the environmental conditions. A failure to address these outliers can significantly impact the reliability of underwater localization and navigation systems. This paper proposes a novel outlier rejection algorithm for AUV localization using Voronoi diagrams and query point calculation. The Voronoi diagram divides data space into Voronoi cells that center on ultra-short baseline (USBL) data, and the calculated query point determines if the corresponding USBL data is an inlier. This study conducted experiments acquiring GPS and USBL data simultaneously and optimized the algorithm empirically based on the acquired data. In addition, the proposed method was applied to a sensor fusion algorithm to verify its effectiveness, resulting in improved pose estimations. The proposed method can be applied to various sensor fusion algorithms as a preprocess and could be used for outlier rejection for other 2D-based location sensors.

Surveying haemoperfusion impact on COVID-19 from machine learning using Shapley values.

Haemoperfusion (HP) is an innovative extracorporeal therapy that utilizes special cartridges to filter the blood, effectively removing pro-inflammatory cytokines, toxins, and pathogens in COVID-19 patients. This retrospective cohort study aimed to assess the clinical benefits of HP for severe COVID-19 cases using Shapley values for machine learning models. The research involved 578 inpatients (≥ 20years old) admitted to Baqiyatallah hospital (Tehran, Iran). The control group (359 patients) received standard treatment, including high doses of corticosteroids (a single 500mg methylprednisolone pulse, followed by 250mg for 2days), categorized as regimen (I). On the other hand, the HP group (219 patients) received regimen II, consisting of the same corticosteroid treatment (regimen I) along with haemoperfusion using Cytosorb H300. The frequency of haemoperfusion sessions varied based on the type of lung involvement determined by chest CT scans. In addition, the value function defines the Shapley value of the th feature for the query point , where the input matrix features represent individual characteristics, drugs, and history and clinical conditions of the patient. Our data showed a favorable clinical response in the HP group compared to the control group. Notably, one-to-three sessions of HP using the CytoSorb® 300 cartridge led to reduced ventilation requirements and mortality rates in severe COVID-19 patients. Shapley values were calculated to evaluate the contribution of haemoperfusion among other factors, such as side effects, medications, and individual characteristics, to COVID-19 patient outcomes. In addition, there is a significant difference between the two groups among the treatments and medications used remdesivir, adalimumab, tocilizumab, favipiravir, Interferon beta-1a, enoxaparin prophylaxis, enoxaparin full dose, heparin prophylaxis, and heparin full dose (P < 0.05). It seems that haemoperfusion has a positive impact on the reduction of inflammation markers and renal functional such as ferritin and creatinine, respectively, as well as D-dimer and WBC levels in the HP group were significantly lower than the control group. The findings indicated that haemoperfusion played a crucial role in predicting patient survival, making it a significant feature in classifying patients' prognoses.

Hypervolume-Guided Decomposition for Parallel Expensive Multiobjective Optimization

The hypervolume metric is widely used to guide the search in multiobjective optimization. However, in parallel expensive multiobjective optimization, the hypervolume-based multi-point expected improvement (EI) suffers from high computational overhead and scales poorly with the batch size. To address this issue, we integrate hypervolume-based EI with the MOEA/D framework and propose a novel EI, named the expected direction-based hypervolume improvement (DirHV-EI). The DirHV-EI only measures the hypervolume improvement within each axis-parallel box induced by the modified Tchebycheff scalarization. Thus, it has a simple analytical expression that can be easily computed. Theoretical analysis indicates that the maximization of our proposed improvement function can help to maximize both the weighted hypervolume and the Tchebycheff improvement metrics. Using DirHV-EI, we design a decomposition-based Bayesian optimization algorithm, called DirHV-EGO, for solving expensive multiobjective optimization problems. At each iteration, the MOEA/D is used to maximize the DirHV-EI values with respect to a number of direction vectors in a collaborative manner, and a number of candidate solutions can be obtained. Then, a submodularity-based greedy selection strategy is used to select multiple query points from the candidates. Experimental results on both benchmark instances and real-world problems show that our proposed algorithm is an efficient and effective method for parallel expensive multiobjective optimization.

Advanced Planar Projection Contour (PPC): A Novel Algorithm for Local Feature Description in Point Clouds.

Local feature description of point clouds is essential in 3D computer vision. However, many local feature descriptors for point clouds struggle with inadequate robustness, excessive dimensionality, and poor computational efficiency. To address these issues, we propose a novel descriptor based on Planar Projection Contours, characterized by convex packet contour information. We construct the Local Reference Frame (LRF) through covariance analysis of the query point and its neighboring points. Neighboring points are projected onto three orthogonal planes defined by the LRF. These projection points on the planes are fitted into convex hull contours and encoded as local features. These planar features are then concatenated to create the Planar Projection Contour (PPC) descriptor. We evaluated the performance of the PPC descriptor against classical descriptors using the B3R, UWAOR, and Kinect datasets. Experimental results demonstrate that the PPC descriptor achieves an accuracy exceeding 80% across all recall levels, even under high-noise and point density variation conditions, underscoring its effectiveness and robustness.

Fast and exact fixed-radius neighbor search based on sorting.

Fixed-radius near neighbor search is a fundamental data operation that retrieves all data points within a user-specified distance to a query point. There are efficient algorithms that can provide fast approximate query responses, but they often have a very compute-intensive indexing phase and require careful parameter tuning. Therefore, exact brute force and tree-based search methods are still widely used. Here we propose a new fixed-radius near neighbor search method, called SNN, that significantly improves over brute force and tree-based methods in terms of index and query time, provably returns exact results, and requires no parameter tuning. SNN exploits a sorting of the data points by their first principal component to prune the query search space. Further speedup is gained from an efficient implementation using high-level basic linear algebra subprograms (BLAS). We provide theoretical analysis of our method and demonstrate its practical performance when used stand-alone and when applied within the DBSCAN clustering algorithm.

Adaptive locally weighted support vector algorithm with asymmetrically parametric insensitive/margin model

In many fields such as finance and electrical load, locally weighted support vector regression (LWSVR) method can achieve better prediction results by constructing different sub-models for each prediction target. However, it selected a fixed and single nearest neighbor parameter of kglobal for each query, and adopted the traditional k-nearest neighbor (KNN) algorithm, which is suboptimal. The weights in LWSVR assigned to the neighboring sample points also affected the accuracy of the model predictions. In this paper, we propose an adaptive locally weighted support vector regression with asymmetrically parametric insensitive/margin model, called Asy-par-v-ALWSVR. Since the selection of similar sample for query points is significant. We propose a novel locally q-neighbour selection algorithm that adaptively selects the most suitable number of neighbours for each query point based on Mahalanobis distance, rather than using a fixed kglobal. This significantly improves prediction accuracy. The weights of neighbours for each query point in Asy-par-v-ALWSVR is based on the distance within the kernel-induced feature space. This effectively discerns the importance of samples during the training process. In particular, Asy-par-v-ALWSVR can handle skewed noise with heteroscedastic structure in regression problems. Finally, we evaluate the proposed model on a synthetic sinc dataset and 14 real datasets. The results demonstrate that Asy-par-v-ALWSVR outperforms six state-of-the-art SVR-based models.

Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling

Point cloud upsampling aims to generate dense and uniformly distributed point sets from a sparse point cloud, which plays a critical role in 3D computer vision. Previous methods typically split a sparse point cloud into several local patches, upsample patch points, and merge all upsampled patches. However, these methods often produce holes, outliers or non-uniformity due to the splitting and merging process which does not maintain consistency among local patches.To address these issues, we propose a novel approach that learns an unsigned distance field guided by local priors for point cloud upsampling. Specifically, we train a local distance indicator (LDI) that predicts the unsigned distance from a query point to a local implicit surface. Utilizing the learned LDI, we learn an unsigned distance field to represent the sparse point cloud with patch consistency. At inference time, we randomly sample queries around the sparse point cloud, and project these query points onto the zero-level set of the learned implicit field to generate a dense point cloud. We justify that the implicit field is naturally continuous, which inherently enables the application of arbitrary-scale upsampling without necessarily retraining for various scales. We conduct comprehensive experiments on both synthetic data and real scans, and report state-of-the-art results under widely used benchmarks. Project page: https://lisj575.github.io/APU-LDI

LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions

Implicit 3D surface reconstruction of an object from its partial and noisy 3D point cloud scan is the classical geometry processing and 3D computer vision problem. In the literature, various 3D shape representations have been developed, differing in memory efficiency and shape retrieval effectiveness, such as volumetric, parametric, and implicit surfaces. Radial basis functions provide memory-efficient parameterization of the implicit surface. However, we show that training a neural network using the mean squared error between the ground-truth implicit surface and the linear basis-based implicit surfaces does not converge to the global solution. In this work, we propose locally supported compact radial basis functions for a linear representation of the implicit surface. This representation enables us to generate 3D shapes with arbitrary topologies at any resolution due to their continuous nature. We then propose a neural network architecture for learning the linear implicit shape representation of the 3D surface of an object. We learn linear implicit shapes within a supervised learning framework using ground truth Signed-Distance Field (SDF) data for guidance. The classical strategies face difficulties in finding linear implicit shapes from a given 3D point cloud due to numerical issues (requires solving inverse of a large matrix) in basis and query point selection. The proposed approach achieves better Chamfer distance and comparable F-score than the state-of-the-art approach on the benchmark dataset. We also show the effectiveness of the proposed approach by using it for the 3D shape completion task.

Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis

Recently MLP-based methods have shown strong performance in point cloud analysis. Simple MLP architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. In this paper, we propose Point Deformable Network (PDNet), a concise MLP-based network that can capture long-range relations with strong representation ability. Specifically, we put forward Point Deformable Aggregation Module (PDAM) to improve representation capability in both long-range dependency and adaptive aggregation among points. For each query point, PDAM aggregates information from deformable reference points rather than points in limited local areas. The deformable reference points are generated data-dependent, and we initialize them according to the input point positions. Additional offsets and modulation scalars are learned on the whole point features, which shift the deformable reference points to the regions of interest. We also suggest estimating the normal vector for point clouds and applying Enhanced Normal Embedding (ENE) to the geometric extractors to improve the representation ability of single-point. Extensive experiments and ablation studies on various benchmarks demonstrate the effectiveness and superiority of our PDNet.

3D Visibility-Aware Generalizable Neural Radiance Fields for Interacting Hands

Neural radiance fields (NeRFs) are promising 3D representations for scenes, objects, and humans. However, most existing methods require multi-view inputs and per-scene training, which limits their real-life applications. Moreover, current methods focus on single-subject cases, leaving scenes of interacting hands that involve severe inter-hand occlusions and challenging view variations remain unsolved. To tackle these issues, this paper proposes a generalizable visibility-aware NeRF (VA-NeRF) framework for interacting hands. Specifically, given an image of interacting hands as input, our VA-NeRF first obtains a mesh-based representation of hands and extracts their corresponding geometric and textural features. Subsequently, a feature fusion module that exploits the visibility of query points and mesh vertices is introduced to adaptively merge features of both hands, enabling the recovery of features in unseen areas. Additionally, our VA-NeRF is optimized together with a novel discriminator within an adversarial learning paradigm. In contrast to conventional discriminators that predict a single real/fake label for the synthesized image, the proposed discriminator generates a pixel-wise visibility map, providing fine-grained supervision for unseen areas and encouraging the VA-NeRF to improve the visual quality of synthesized images. Experiments on the Interhand2.6M dataset demonstrate that our proposed VA-NeRF outperforms conventional NeRFs significantly. Project Page: https://github.com/XuanHuang0/VANeRF.

Grey-Box Bayesian Optimization for Sensor Placement in Assisted Living Environments

Optimizing the configuration and placement of sensors is crucial for reliable fall detection, indoor localization, and activity recognition in assisted living spaces. We propose a novel, sample-efficient approach to find a high-quality sensor placement in an arbitrary indoor space based on grey-box Bayesian optimization and simulation-based evaluation. Our key technical contribution lies in capturing domain-specific knowledge about the spatial distribution of activities and incorporating it into the iterative selection of query points in Bayesian optimization. Considering two simulated indoor environments and a real-world dataset containing human activities and sensor triggers, we show that our proposed method performs better compared to state-of-the-art black-box optimization techniques in identifying high-quality sensor placements, leading to an accurate activity recognition model in terms of F1-score, while also requiring a significantly lower (51.3% on average) number of expensive function queries.

End-to-End Real-Time Vanishing Point Detection with Transformer

In this paper, we propose a novel transformer-based end-to-end real-time vanishing point detection method, which is named Vanishing Point TRansformer (VPTR). The proposed method can directly regress the locations of vanishing points from given images. To achieve this goal, we pose vanishing point detection as a point object detection task on the Gaussian hemisphere with region division. Considering low-level features always provide more geometric information which can contribute to accurate vanishing point prediction, we propose a clear architecture where vanishing point queries in the decoder can directly gather multi-level features from CNN backbone with deformable attention in VPTR. Our method does not rely on line detection or Manhattan world assumption, which makes it more flexible to use. VPTR runs at an inferring speed of 140 FPS on one NVIDIA 3090 card. Experimental results on synthetic and real-world datasets demonstrate that our method can be used in both natural and structural scenes, and is superior to other state-of-the-art methods on the balance of accuracy and efficiency.

One Seed, Two Birds: A Unified Learned Structure for Exact and Approximate Counting

The modern database has many precise and approximate counting requirements. Nevertheless, a solitary multidimensional index or cardinality estimator is insufficient to cater to the escalating demands across all counting scenarios. Such approaches are constrained either by query selectivity or by the compromise between query accuracy and efficiency. We propose CardIndex, a unified learned structure to solve the above problems. CardIndex serves as a versatile solution that not only functions as a multidimensional learned index for accurate counting but also doubles as an adaptive cardinality estimator, catering to varying counting scenarios with diverse requirements for precision and efficiency. Rigorous experimentation has showcased its superiority. Compared to the state-of-the-art (SOTA) autoregressive data-driven cardinality estimation baselines, our structure achieves training and updating times that are two orders of magnitude faster. Additionally, our CPU-based query estimation latency surpasses GPU-based baselines by two to three times. Notably, the estimation accuracy of low-selectivity queries is up to 314 times better than the current SOTA estimator. In terms of indexing tasks, the construction speed of our structure is two orders of magnitude faster than RSMI and 1.9 times faster than R-tree. Furthermore, it exhibits a point query processing speed that is 3%-17% times faster than RSMI and 1.07 to 2.75 times faster than R-tree and KDB-tree. Range queries under specific loads are 20% times faster than the SOTA indexes.