Dewen Hu

Zheng Qin, Hao Yu, Changjian Wang et al.

We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods have shown great potential through bypassing the detection of repeatable keypoints which is difficult to do especially in low-overlap scenarios. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer, or GeoTransformer for short, to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it invariant to rigid transformation and robust in low-overlap cases. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to $100$ times acceleration. Extensive experiments on rich benchmarks encompassing indoor, outdoor, synthetic, multiway and non-rigid demonstrate the efficacy of GeoTransformer. Notably, our method improves the inlier ratio by $18{\sim}31$ percentage points and the registration recall by over $7$ points on the challenging 3DLoMatch benchmark. Our code and models are available at \url{https://github.com/qinzheng93/GeoTransformer}.

Bo Wang, Yifan Zhang, Jian Li et al.

The occlusion problem remains a crucial challenge in optical flow estimation (OFE). Despite the recent significant progress brought about by deep learning, most existing deep learning OFE methods still struggle to handle occlusions; in particular, those based on two frames cannot correctly handle occlusions because occluded regions have no visual correspondences. However, there is still hope in multi-frame settings, which can potentially mitigate the occlusion issue in OFE. Unfortunately, multi-frame OFE (MOFE) remains underexplored, and the limited studies on it are mainly specially designed for pyramid backbones or else obtain the aligned previous frame's features, such as correlation volume and optical flow, through time-consuming backward flow calculation or non-differentiable forward warping transformation. This study proposes an efficient MOFE framework named SplatFlow to address these shortcomings. SplatFlow introduces the differentiable splatting transformation to align the previous frame's motion feature and designs a Final-to-All embedding method to input the aligned motion feature into the current frame's estimation, thus remodeling the existing two-frame backbones. The proposed SplatFlow is efficient yet more accurate, as it can handle occlusions properly. Extensive experimental evaluations show that SplatFlow substantially outperforms all published methods on the KITTI2015 and Sintel benchmarks. Especially on the Sintel benchmark, SplatFlow achieves errors of 1.12 (clean pass) and 2.07 (final pass), with surprisingly significant 19.4% and 16.2% error reductions, respectively, from the previous best results submitted. The code for SplatFlow is available at https://github.com/wwsource/SplatFlow.

Yuanxin Wu, Hongliang Zhang, Meiping Wu et al.

Alignment of the strapdown inertial navigation system (INS) has strong nonlinearity, even worse when maneuvers, e.g., tumbling techniques, are employed to improve the alignment. There is no general rule to attack the observability of a nonlinear system, so most previous works addressed the observability of the corresponding linearized system by implicitly assuming that the original nonlinear system and the linearized one have identical observability characteristics. Strapdown INS alignment is a nonlinear system that has its own characteristics. Using the inherent properties of strapdown INS, e.g., the attitude evolution on the SO(3) manifold, we start from the basic definition and develop a global and constructive approach to investigate the observability of strapdown INS static and tumbling alignment, highlighting the effects of the attitude maneuver on observability. We prove that strapdown INS alignment, considering the unknown constant sensor biases, will be completely observable if the strapdown INS is rotated successively about two different axes and will be nearly observable for finite known unobservable states (no more than two) if it is rotated about a single axis. Observability from a global perspective provides us with insights into and a clearer picture of the problem, shedding light on previous theoretical results on strapdown INS alignment that were not comprehensive or consistent.. The reporting of inconsistencies calls for a review of all linearization-based observability studies in the vast literature. Extensive simulations with constructed ideal observers and an extended Kalman filter are carried out, and the numerical results accord with the analysis. The conclusions can also assist in designing the optimal tumbling strategy and the appropriate state observer in practice to maximize the alignment performance.

Zhenhua Du, Zhen Tan, Haoyu Zhang et al.

While 3D Gaussian Splatting has achieved remarkable success in photorealistic novel view synthesis, its pursuit of fast and high-fidelity 3D reconstruction has long been constrained by a trade-off between geometric accuracy and optimization efficiency. Methods specialized in image rendering converge quickly at the cost of imperfect geometry caused by superfluous primitives overfitting training views, while methods integrating neural signed-distance field (SDF) for better geometry incur prohibitive training costs. In this paper, we attempt to strike a better trade-off by tethering scaffold-anchored Gaussians to a jointly optimized sparse voxel scaffold. This hybrid Gaussian-Voxel representation explicitly confines anchored Gaussians to a narrow band around surfaces defined by voxelized SDFs, which effectively improves representation efficiency and condenses floating Gaussians without sacrificing geometry quality. An implicit surface tethering loss further pulls individual Gaussian primitives closer to SDF-induced surfaces in a mutually regularized manner for improved reconstruction accuracy. Extensive experiments on diverse real-world indoor scenes from ScanNet++, ScanNetv2, and DeepBlending datasets demonstrate that our method achieves state-of-the-art surface reconstruction quality as well as superior novel view synthesis against leading baselines, while maintaining fast training convergence and real-time rendering. Code will be available at https://github.com/duzh11/VoxelGS.

Jinghua Zhang, Li Liu, Kai Gao et al.

Automatic Pill Recognition (APR) systems are crucial for enhancing hospital efficiency, assisting visually impaired individuals, and preventing cross-infection. However, most existing deep learning-based pill recognition systems can only perform classification on classes with sufficient training data. In practice, the high cost of data annotation and the continuous increase in new pill classes necessitate the development of a few-shot class-incremental pill recognition system. This paper introduces the first few-shot class-incremental pill recognition framework, named Discriminative and Bidirectional Compatible Few-Shot Class-Incremental Learning (DBC-FSCIL). It encompasses forward-compatible and backward-compatible learning components. In forward-compatible learning, we propose an innovative virtual class synthesis strategy and a Center-Triplet (CT) loss to enhance discriminative feature learning. These virtual classes serve as placeholders in the feature space for future class updates, providing diverse semantic knowledge for model training. For backward-compatible learning, we develop a strategy to synthesize reliable pseudo-features of old classes using uncertainty quantification, facilitating Data Replay (DR) and Knowledge Distillation (KD). This approach allows for the flexible synthesis of features and effectively reduces additional storage requirements for samples and models. Additionally, we construct a new pill image dataset for FSCIL and assess various mainstream FSCIL methods, establishing new benchmarks. Our experimental results demonstrate that our framework surpasses existing State-of-the-art (SOTA) methods. The code is available at https://github.com/zhang-jinghua/DBC-FSCIL.

Jinghua Zhang, Li Liu, Olli Silvén et al.

Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine Learning (ML), as it necessitates the Incremental Learning (IL) of new classes from sparsely labeled training samples without forgetting previous knowledge. While this field has seen recent progress, it remains an active exploration area. This paper aims to provide a comprehensive and systematic review of FSCIL. In our in-depth examination, we delve into various facets of FSCIL, encompassing the problem definition, the discussion of the primary challenges of unreliable empirical risk minimization and the stability-plasticity dilemma, general schemes, and relevant problems of IL and Few-shot Learning (FSL). Besides, we offer an overview of benchmark datasets and evaluation metrics. Furthermore, we introduce the Few-shot Class-incremental Classification (FSCIC) methods from data-based, structure-based, and optimization-based approaches and the Few-shot Class-incremental Object Detection (FSCIOD) methods from anchor-free and anchor-based approaches. Beyond these, we present several promising research directions within FSCIL that merit further investigation.

Yifei Shi, Junhua Xi, Dewen Hu et al.

Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from most existing works dedicated to adaptive refinement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth. This sequential modeling, conducted based on transformer features, essentially learns the epipolar line search in traditional multi-view stereo. We devise a multi-task learning for better optimization convergence and depth accuracy. We found the monotonicity property of the SDFs along each ray greatly benefits the depth estimation. Our method ranks top on both the DTU and the Tanks & Temples datasets over all previous learning-based methods, achieving an overall reconstruction score of 0.33mm on DTU and an F-score of 59.48% on Tanks & Temples. It is able to produce high-quality depth estimation and point cloud reconstruction in challenging scenarios such as objects/scenes with non-textured surface, severe occlusion, and highly varying depth range. Further, we propose RayMVSNet++ to enhance contextual feature aggregation for each ray through designing an attentional gating unit to select semantically relevant neighboring rays within the local frustum around that ray. RayMVSNet++ achieves state-of-the-art performance on the ScanNet dataset. In particular, it attains an AbsRel of 0.058m and produces accurate results on the two subsets of textureless regions and large depth variation.

Jiaxiong Liu, Bo Wang, Zhen Tan et al.

Tracking any point based on image frames is constrained by frame rates, leading to instability in high-speed scenarios and limited generalization in real-world applications. To overcome these limitations, we propose an image-event fusion point tracker, FE-TAP, which combines the contextual information from image frames with the high temporal resolution of events, achieving high frame rate and robust point tracking under various challenging conditions. Specifically, we designed an Evolution Fusion module (EvoFusion) to model the image generation process guided by events. This module can effectively integrate valuable information from both modalities operating at different frequencies. To achieve smoother point trajectories, we employed a transformer-based refinement strategy that updates the point's trajectories and features iteratively. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches, particularly improving expected feature age by 24$\%$ on EDS datasets. Finally, we qualitatively validated the robustness of our algorithm in real driving scenarios using our custom-designed high-resolution image-event synchronization device. Our source code will be released at https://github.com/ljx1002/FE-TAP.

Zhongyan Niu, Zhen Tan, Jinpu Zhang et al.

Visual localization refers to the process of determining camera poses and orientation within a known scene representation. This task is often complicated by factors such as changes in illumination and variations in viewing angles. In this paper, we propose HGSLoc, a novel lightweight plug-and-play pose optimization framework, which integrates 3D reconstruction with a heuristic refinement strategy to achieve higher pose estimation accuracy. Specifically, we introduce an explicit geometric map for 3D representation and high-fidelity rendering, allowing the generation of high-quality synthesized views to support accurate visual localization. Our method demonstrates higher localization accuracy compared to NeRF-based neural rendering localization approaches. We introduce a heuristic refinement strategy, its efficient optimization capability can quickly locate the target node, while we set the step level optimization step to enhance the pose accuracy in the scenarios with small errors. With carefully designed heuristic functions, it offers efficient optimization capabilities, enabling rapid error reduction in rough localization estimations. Our method mitigates the dependence on complex neural network models while demonstrating improved robustness against noise and higher localization accuracy in challenging environments, as compared to neural network joint optimization strategies. The optimization framework proposed in this paper introduces novel approaches to visual localization by integrating the advantages of 3D reconstruction and the heuristic refinement strategy, which demonstrates strong performance across multiple benchmark datasets, including 7Scenes and Deep Blending dataset. The implementation of our method has been released at https://github.com/anchang699/HGSLoc.

Yang Yi, Xieyuanli Chen, Jinpu Zhang et al.

Robust local feature detection and description are foundational tasks in computer vision. Existing methods primarily rely on single appearance cues for modeling, leading to unstable keypoints and insufficient descriptor discriminability. In this paper, we propose a multi-cue guided local feature learning framework that leverages semantic and geometric cues to synergistically enhance detection robustness and descriptor discriminability. Specifically, we construct a joint semantic-normal prediction head and a depth stability prediction head atop a lightweight backbone. The former leverages a shared 3D vector field to deeply couple semantic and normal cues, thereby resolving optimization interference from heterogeneous inconsistencies. The latter quantifies the reliability of local regions from a geometric consistency perspective, providing deterministic guidance for robust keypoint selection. Based on these predictions, we introduce the Semantic-Depth Aware Keypoint (SDAK) mechanism for feature detection. By coupling semantic reliability with depth stability, SDAK reweights keypoint responses to suppress spurious features in unreliable regions. For descriptor construction, we design a Unified Triple-Cue Fusion (UTCF) module, which employs a semantic-scheduled gating mechanism to adaptively inject multi-attribute features, improving descriptor discriminability. Extensive experiments on four benchmarks validate the effectiveness of the proposed framework. The source code and pre-trained model will be available at: https://github.com/yiyscut/GESS.git.

Jiaxiang Li, Zongtan Zhou, Zhen Tan et al.

Reconstructing high-quality 3D scenes from low-resolution multi-view images remains challenging for 3D Gaussian Splatting (3DGS), because insufficient high-frequency observations often lead to blurred textures, weak boundaries, and view-inconsistent details. Existing approaches either apply super-resolution guidance uniformly or localize enhancement regions based mainly on geometric sampling. However, they typically do not distinguish between two fundamentally different questions: where additional detail is needed, and whether the corresponding candidate high-frequency content is reliable enough to be internalized into a multi-view consistent 3D representation. In this paper, we propose a reliability-aware frequency modeling framework for low-resolution 3DGS reconstruction. The framework first estimates a geometry-guided detail-demand prior to locate regions that are likely under-detailed under low-resolution supervision. It then computes a frequency-aware reliability map to determine whether candidate high-frequency details are structurally supported, spectrally unresolved, and cross-view stable. Combining these signals yields a detail-injection map that guides where super-resolved details should be introduced during optimization. Based on this map, we design a unified optimization scheme comprising spatially selective supervision, coarse-to-fine frequency regularization, and reliability-aware Gaussian densification. This scheme controls where reliable details are injected, when high-frequency supervision is activated, and how unresolved yet reliable details are internalized into the Gaussian representation. Experiments on multiple benchmarks show improved fidelity and perceptual quality while suppressing unstable or view-inconsistent details.

Bo Wang, Jian Li, Yang Yu et al.

Considering that scene flow estimation has the capability of the spatial domain to focus but lacks the coherence of the temporal domain, this study proposes long-term scene flow estimation (LSFE), a comprehensive task that can simultaneously capture the fine-grained and long-term 3D motion in an online manner. We introduce SceneTracker, the first LSFE network that adopts an iterative approach to approximate the optimal 3D trajectory. The network dynamically and simultaneously indexes and constructs appearance correlation and depth residual features. Transformers are then employed to explore and utilize long-range connections within and between trajectories. With detailed experiments, SceneTracker shows superior capabilities in addressing 3D spatial occlusion and depth noise interference, highly tailored to the needs of the LSFE task. We build a real-world evaluation dataset, LSFDriving, for the LSFE field and use it in experiments to further demonstrate the advantage of SceneTracker in generalization abilities. The code and data are available at https://github.com/wwsource/SceneTracker.

Zhen Tan, Zongtan Zhou, Yangbing Ge et al.

The reliance on accurate camera poses is a significant barrier to the widespread deployment of Neural Radiance Fields (NeRF) models for 3D reconstruction and SLAM tasks. The existing method introduces monocular depth priors to jointly optimize the camera poses and NeRF, which fails to fully exploit the depth priors and neglects the impact of their inherent noise. In this paper, we propose Truncated Depth NeRF (TD-NeRF), a novel approach that enables training NeRF from unknown camera poses - by jointly optimizing learnable parameters of the radiance field and camera poses. Our approach explicitly utilizes monocular depth priors through three key advancements: 1) we propose a novel depth-based ray sampling strategy based on the truncated normal distribution, which improves the convergence speed and accuracy of pose estimation; 2) to circumvent local minima and refine depth geometry, we introduce a coarse-to-fine training strategy that progressively improves the depth precision; 3) we propose a more robust inter-frame point constraint that enhances robustness against depth noise during training. The experimental results on three datasets demonstrate that TD-NeRF achieves superior performance in the joint optimization of camera pose and NeRF, surpassing prior works, and generates more accurate depth geometry. The implementation of our method has been released at https://github.com/nubot-nudt/TD-NeRF.

Zhen Tan, Xieyuanli Chen, Jinpu Zhang et al.

3D Gaussian Splatting (3DGS) has achieved impressive rendering performance in novel view synthesis. However, its efficacy diminishes considerably in sparse image sequences, where inherent data sparsity amplifies geometric uncertainty during optimization. This often leads to convergence at suboptimal local minima, resulting in noticeable structural artifacts in the reconstructed scenes.To mitigate these issues, we propose Uncertainty-aware Normal-Guided Gaussian Splatting (UNG-GS), a novel framework featuring an explicit Spatial Uncertainty Field (SUF) to quantify geometric uncertainty within the 3DGS pipeline. UNG-GS enables high-fidelity rendering and achieves high-precision reconstruction without relying on priors. Specifically, we first integrate Gaussian-based probabilistic modeling into the training of 3DGS to optimize the SUF, providing the model with adaptive error tolerance. An uncertainty-aware depth rendering strategy is then employed to weight depth contributions based on the SUF, effectively reducing noise while preserving fine details. Furthermore, an uncertainty-guided normal refinement method adjusts the influence of neighboring depth values in normal estimation, promoting robust results. Extensive experiments demonstrate that UNG-GS significantly outperforms state-of-the-art methods in both sparse and dense sequences. The code will be open-source.

Zhen Tan, Xieyuanli Chen, Lei Feng et al.

Recent advances in 3D Gaussian Splatting (3DGS) have enabled RGB-only SLAM systems to achieve high-fidelity scene representation. However, the heavy reliance of existing systems on photometric rendering loss for camera tracking undermines their robustness, especially in unbounded outdoor environments with severe viewpoint and illumination changes. To address these challenges, we propose TVG-SLAM, a robust RGB-only 3DGS SLAM system that leverages a novel tri-view geometry paradigm to ensure consistent tracking and high-quality mapping. We introduce a dense tri-view matching module that aggregates reliable pairwise correspondences into consistent tri-view matches, forming robust geometric constraints across frames. For tracking, we propose Hybrid Geometric Constraints, which leverage tri-view matches to construct complementary geometric cues alongside photometric loss, ensuring accurate and stable pose estimation even under drastic viewpoint shifts and lighting variations. For mapping, we propose a new probabilistic initialization strategy that encodes geometric uncertainty from tri-view correspondences into newly initialized Gaussians. Additionally, we design a Dynamic Attenuation of Rendering Trust mechanism to mitigate tracking drift caused by mapping latency. Experiments on multiple public outdoor datasets show that our TVG-SLAM outperforms prior RGB-only 3DGS-based SLAM systems. Notably, in the most challenging dataset, our method improves tracking robustness, reducing the average Absolute Trajectory Error (ATE) by 69.0\% while achieving state-of-the-art rendering quality. The implementation of our method will be released as open-source.

Zhuo Su, Wenzhe Liu, Zitong Yu et al.

Recently, deep Convolutional Neural Networks (CNNs) can achieve human-level performance in edge detection with the rich and abstract edge representation capacities. However, the high performance of CNN based edge detection is achieved with a large pretrained CNN backbone, which is memory and energy consuming. In addition, it is surprising that the previous wisdom from the traditional edge detectors, such as Canny, Sobel, and LBP are rarely investigated in the rapid-developing deep learning era. To address these issues, we propose a simple, lightweight yet effective architecture named Pixel Difference Network (PiDiNet) for efficient edge detection. Extensive experiments on BSDS500, NYUD, and Multicue are provided to demonstrate its effectiveness, and its high training and inference efficiency. Surprisingly, when training from scratch with only the BSDS500 and VOC datasets, PiDiNet can surpass the recorded result of human perception (0.807 vs. 0.803 in ODS F-measure) on the BSDS500 dataset with 100 FPS and less than 1M parameters. A faster version of PiDiNet with less than 0.1M parameters can still achieve comparable performance among state of the arts with 200 FPS. Results on the NYUD and Multicue datasets show similar observations. The codes are available at https://github.com/zhuoinoulu/pidinet.

Zhuo Su, Linpu Fang, Deke Guo et al.

Binary neural networks (BNNs), where both weights and activations are binarized into 1 bit, have been widely studied in recent years due to its great benefit of highly accelerated computation and substantially reduced memory footprint that appeal to the development of resource constrained devices. In contrast to previous methods tending to reduce the quantization error for training BNN structures, we argue that the binarized convolution process owns an increasing linearity towards the target of minimizing such error, which in turn hampers BNN's discriminative ability. In this paper, we re-investigate and tune proper non-linear modules to fix that contradiction, leading to a strong baseline which achieves state-of-the-art performance on the large-scale ImageNet dataset in terms of accuracy and training efficiency. To go further, we find that the proposed BNN model still has much potential to be compressed by making a better use of the efficient binary operations, without losing accuracy. In addition, the limited capacity of the BNN model can also be increased with the help of group execution. Based on these insights, we are able to improve the baseline with an additional 4~5% top-1 accuracy gain even with less computational cost. Our code will be made public at https://github.com/zhuogege1943/ftbnn.

Zhuo Su, Linpu Fang, Wenxiong Kang et al.

Replacing normal convolutions with group convolutions can significantly increase the computational efficiency of modern deep convolutional networks, which has been widely adopted in compact network architecture designs. However, existing group convolutions undermine the original network structures by cutting off some connections permanently resulting in significant accuracy degradation. In this paper, we propose dynamic group convolution (DGC) that adaptively selects which part of input channels to be connected within each group for individual samples on the fly. Specifically, we equip each group with a small feature selector to automatically select the most important input channels conditioned on the input images. Multiple groups can adaptively capture abundant and complementary visual/semantic features for each input image. The DGC preserves the original network structure and has similar computational efficiency as the conventional group convolution simultaneously. Extensive experiments on multiple image classification benchmarks including CIFAR-10, CIFAR-100 and ImageNet demonstrate its superiority over the existing group convolution techniques and dynamic execution methods. The code is available at https://github.com/zhuogege1943/dgc.

Sheng Zhong, Junkai Niu, Guillermo Gallego et al.

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 visual tasks in high-speed maneuvering scenarios. Existing event-based approaches, although successful in mitigating motion blur caused by high-speed maneuvers, suffer from many limitations. Some of them highlight a success of pose tracking for a fronto-parallel fast shaking camera closed to the structure, while others assume pure (optionally aggressive) three-degree-of-freedom rotations. The former requires persistent local map visibility within the field of view (FOV), whereas the latter fails to generalize to six-degree-of-freedom (6-DoF) motions where both linear and angular velocities may be large. Consequently, current successes do not fully demonstrate that event-based state estimation under arbitrary aggressive maneuvers is a fully solved problem. To quantitatively assess the extent to which the potential of event cameras has been unlocked, we conduct a thorough analysis of state-of-the-art (SOTA) event-based visual odometry (VO)/visual-inertial odometry (VIO) methods and report shortcomings in current public datasets. Furthermore, we introduce a benchmarking framework for event-based state estimation, called EvSLAM, characterized by sufficient variation in data collection platforms, diverse extreme lighting scenarios, and a wide scope of challenging motion patterns under a clear and rigorous definition of high-speed maneuvers for mobile robots, along with a novel evaluation metric designed to fairly assess the operational limits of event-based solutions. This framework benchmarks state-of-the-art methods, yielding insights into optimal architectures and persistent challenges.

Xinglong Zhang, Wei Pan, Cong Li et al.

Distributed model predictive control (DMPC) is promising in achieving optimal cooperative control in multirobot systems (MRS). However, real-time DMPC implementation relies on numerical optimization tools to periodically calculate local control sequences online. This process is computationally demanding and lacks scalability for large-scale, nonlinear MRS. This article proposes a novel distributed learning-based predictive control (DLPC) framework for scalable multirobot control. Unlike conventional DMPC methods that calculate open-loop control sequences, our approach centers around a computationally fast and efficient distributed policy learning algorithm that generates explicit closed-loop DMPC policies for MRS without using numerical solvers. The policy learning is executed incrementally and forward in time in each prediction interval through an online distributed actor-critic implementation. The control policies are successively updated in a receding-horizon manner, enabling fast and efficient policy learning with the closed-loop stability guarantee. The learned control policies could be deployed online to MRS with varying robot scales, enhancing scalability and transferability for large-scale MRS. Furthermore, we extend our methodology to address the multirobot safe learning challenge through a force field-inspired policy learning approach. We validate our approach's effectiveness, scalability, and efficiency through extensive experiments on cooperative tasks of large-scale wheeled robots and multirotor drones. Our results demonstrate the rapid learning and deployment of DMPC policies for MRS with scales up to 10,000 units.

Jiaxiong Liu, Zhen Tan, Jinpu Zhang et al.

Tracking any point (TAP) is a fundamental yet challenging task in computer vision, requiring high precision and long-term motion reasoning. Recent attempts to combine RGB frames and event streams have shown promise, yet they typically rely on synchronous or non-adaptive fusion, leading to temporal misalignment and severe degradation when one modality fails. We introduce TAPFormer, a transformer-based framework that performs asynchronous temporal-consistent fusion of frames and events for robust and high-frequency arbitrary point tracking. Our key innovation is a Transient Asynchronous Fusion (TAF) mechanism, which explicitly models the temporal evolution between discrete frames through continuous event updates, bridging the gap between low-rate frames and high-rate events. In addition, a Cross-modal Locally Weighted Fusion (CLWF) module adaptively adjusts spatial attention according to modality reliability, yielding stable and discriminative features even under blur or low light. To evaluate our approach under realistic conditions, we construct a novel real-world frame-event TAP dataset under diverse illumination and motion conditions. Our method outperforms existing point trackers, achieving a 28.2% improvement in average pixel error within threshold. Moreover, on standard point tracking benchmarks, our tracker consistently achieves the best performance. Project website: tapformer.github.io

Ce Guo, Xieyuanli Chen, Zhiwen Zeng et al.

Tactile and kinesthetic perceptions are crucial for human dexterous manipulation, enabling reliable grasping of objects via proprioceptive sensorimotor integration. For robotic hands, even though acquiring such tactile and kinesthetic feedback is feasible, establishing a direct mapping from this sensory feedback to motor actions remains challenging. In this paper, we propose a novel glove-mediated tactile-kinematic perception-prediction framework for grasp skill transfer from human intuitive and natural operation to robotic execution based on imitation learning, and its effectiveness is validated through generalized grasping tasks, including those involving deformable objects. Firstly, we integrate a data glove to capture tactile and kinesthetic data at the joint level. The glove is adaptable for both human and robotic hands, allowing data collection from natural human hand demonstrations across different scenarios. It ensures consistency in the raw data format, enabling evaluation of grasping for both human and robotic hands. Secondly, we establish a unified representation of multi-modal inputs based on graph structures with polar coordinates. We explicitly integrate the morphological differences into the designed representation, enhancing the compatibility across different demonstrators and robotic hands. Furthermore, we introduce the Tactile-Kinesthetic Spatio-Temporal Graph Networks (TK-STGN), which leverage multidimensional subgraph convolutions and attention-based LSTM layers to extract spatio-temporal features from graph inputs to predict node-based states for each hand joint. These predictions are then mapped to final commands through a force-position hybrid mapping.

Jingjun Yang, Liangwei Fan, Jinpu Zhang et al.

The integration of image and event streams offers a promising approach for achieving robust visual object tracking in complex environments. However, current fusion methods achieve high performance at the cost of significant computational overhead and struggle to efficiently extract the sparse, asynchronous information from event streams, failing to leverage the energy-efficient advantages of event-driven spiking paradigms. To address this challenge, we propose the first fully Spiking Frame-Event Tracking framework called SpikeFET. This network achieves synergistic integration of convolutional local feature extraction and Transformer-based global modeling within the spiking paradigm, effectively fusing frame and event data. To overcome the degradation of translation invariance caused by convolutional padding, we introduce a Random Patchwork Module (RPM) that eliminates positional bias through randomized spatial reorganization and learnable type encoding while preserving residual structures. Furthermore, we propose a Spatial-Temporal Regularization (STR) strategy that overcomes similarity metric degradation from asymmetric features by enforcing spatio-temporal consistency among temporal template features in latent space. Extensive experiments across multiple benchmarks demonstrate that the proposed framework achieves superior tracking accuracy over existing methods while significantly reducing power consumption, attaining an optimal balance between performance and efficiency.

Yang Yi, Kunqing Wang, Jinpu Zhang et al.

Accurate and reliable estimation of biases of low-cost Inertial Measurement Units (IMU) is a key factor to maintain the resilience of Visual-Inertial Odometry (VIO), particularly when visual tracking fails in challenging areas. In such cases, bias estimates from the VIO can deviate significantly from the real values because of the insufficient or erroneous vision features, compromising both localization accuracy and system stability. To address this challenge, we propose a novel plug-and-play module featuring the Inertial Prior Network (IPNet), which infers an IMU bias prior by implicitly capturing the motion characteristics of specific platforms. The core idea is inspired intuitively by the observation that different platforms exhibit distinctive motion patterns, while the integration of low-cost IMU measurements suffers from unbounded error that quickly accumulates over time. Therefore, these specific motion patterns can be exploited to infer the underlying IMU bias. In this work, we first directly infer the biases prior only using the raw IMU data using a sliding window approach, eliminating the dependency on recursive bias estimation combining visual features, thus effectively preventing error propagation in challenging areas. Moreover, to compensate for the lack of ground-truth bias in most visual-inertial datasets, we further introduce an iterative method to compute the mean per-sequence IMU bias for network training and release it to benefit society. The framework is trained and evaluated separately on two public datasets and a self-collected dataset. Extensive experiments show that our method significantly improves localization precision and robustness.

Yan Zhao, Lingjun Zhao, Zhong Liu et al.

Aircraft detection in Synthetic Aperture Radar (SAR) imagery is a challenging task in SAR Automatic Target Recognition (SAR ATR) areas due to aircraft's extremely discrete appearance, obvious intraclass variation, small size and serious background's interference. In this paper, a single-shot detector namely Attentional Feature Refinement and Alignment Network (AFRAN) is proposed for detecting aircraft in SAR images with competitive accuracy and speed. Specifically, three significant components including Attention Feature Fusion Module (AFFM), Deformable Lateral Connection Module (DLCM) and Anchor-guided Detection Module (ADM), are carefully designed in our method for refining and aligning informative characteristics of aircraft. To represent characteristics of aircraft with less interference, low-level textural and high-level semantic features of aircraft are fused and refined in AFFM throughly. The alignment between aircraft's discrete back-scatting points and convolutional sampling spots is promoted in DLCM. Eventually, the locations of aircraft are predicted precisely in ADM based on aligned features revised by refined anchors. To evaluate the performance of our method, a self-built SAR aircraft sliced dataset and a large scene SAR image are collected. Extensive quantitative and qualitative experiments with detailed analysis illustrate the effectiveness of the three proposed components. Furthermore, the topmost detection accuracy and competitive speed are achieved by our method compared with other domain-specific,e.g., DAPN, PADN, and general CNN-based methods,e.g., FPN, Cascade R-CNN, SSD, RefineDet and RPDet.

Zhiguo Luo, Ling-Li Zeng, Hui Shen et al.

The frequency-specific coupling mechanism of the functional human brain networks underpins its complex cognitive and behavioral functions. Nevertheless, it is not well unveiled what are the frequency-specific subdivisions and network topologies of the human brain. In this study, we estimated functional connectivity of the human cerebral cortex using spectral connection, and conducted frequency-specific parcellation using eigen-clustering and gradient-based methods, and then explored their topological structures. 7T fMRI data of 184 subjects in the HCP dataset were used for parcellation and exploring the topological properties of the functional networks, and 3T fMRI data of another 890 subjects were used to confirm the stability of the frequency-specific topologies. Seven to ten functional networks were stably integrated by two to four dissociable hub categories at specific frequencies, and we proposed an intrinsic functional atlas containing 456 parcels according to the parcellations across frequencies. The results revealed that the functional networks contained stable frequency-specific topologies, which may imply more abundant roles of the functional units and more complex interactions among them.

Qi Cai, Lilian Zhang, Yuanxin Wu et al.

Visual navigation and three-dimensional (3D) scene reconstruction are essential for robotics to interact with the surrounding environment. Large-scale scenes and critical camera motions are great challenges facing the research community to achieve this goal. We raised a pose-only imaging geometry framework and algorithms that can help solve these challenges. The representation is a linear function of camera global translations, which allows for efficient and robust camera motion estimation. As a result, the spatial feature coordinates can be analytically reconstructed and do not require nonlinear optimization. Experiments demonstrate that the computational efficiency of recovering the scene and associated camera poses is significantly improved by 2-4 orders of magnitude. This solution might be promising to unlock real-time 3D visual computing in many forefront applications.

Delu Zeng, Minyu Liao, Mohammad Tavakolian et al.

Scene classification, aiming at classifying a scene image to one of the predefined scene categories by comprehending the entire image, is a longstanding, fundamental and challenging problem in computer vision. The rise of large-scale datasets, which constitute the corresponding dense sampling of diverse real-world scenes, and the renaissance of deep learning techniques, which learn powerful feature representations directly from big raw data, have been bringing remarkable progress in the field of scene representation and classification. To help researchers master needed advances in this field, the goal of this paper is to provide a comprehensive survey of recent achievements in scene classification using deep learning. More than 200 major publications are included in this survey covering different aspects of scene classification, including challenges, benchmark datasets, taxonomy, and quantitative performance comparisons of the reviewed methods. In retrospect of what has been achieved so far, this paper is also concluded with a list of promising research opportunities.

Hong Tao, Chenping Hou, Dongyun Yi et al.

In real-world applications, not all instances in multi-view data are fully represented. To deal with incomplete data, Incomplete Multi-view Learning (IML) rises. In this paper, we propose the Joint Embedding Learning and Low-Rank Approximation (JELLA) framework for IML. The JELLA framework approximates the incomplete data by a set of low-rank matrices and learns a full and common embedding by linear transformation. Several existing IML methods can be unified as special cases of the framework. More interestingly, some linear transformation based complete multi-view methods can be adapted to IML directly with the guidance of the framework. Thus, the JELLA framework improves the efficiency of processing incomplete multi-view data, and bridges the gap between complete multi-view learning and IML. Moreover, the JELLA framework can provide guidance for developing new algorithms. For illustration, within the framework, we propose the Incomplete Multi-view Learning with Block Diagonal Representation (IML-BDR) method. Assuming that the sampled examples have approximate linear subspace structure, IML-BDR uses the block diagonal structure prior to learn the full embedding, which would lead to more correct clustering. A convergent alternating iterative algorithm with the Successive Over-Relaxation optimization technique is devised for optimization. Experimental results on various datasets demonstrate the effectiveness of IML-BDR.

Chenping Hou, Ling-Li Zeng, Dewen Hu

With the evolution of data collection ways, it is possible to produce abundant data described by multiple feature sets. Previous studies show that including more features does not necessarily bring positive effect. How to prevent the augmented features worsening classification performance is crucial but rarely studied. In this paper, we study this challenging problem by proposing a secure classification approach, whose accuracy is never degenerated when exploiting augmented features. We propose two ways to achieve the security of our method named as SEcure Classification (SEC). Firstly, to leverage augmented features, we learn various types of classifiers and adapt them by employing a specially designed robust loss. It provides various candidate classifiers to meet the following assumption of security operation. Secondly, we integrate all candidate classifiers by approximately maximizing the performance improvement. Under a mild assumption, the integrated classifier has theoretical security guarantee. Several new optimization methods have been developed to accommodate the problems with proved convergence. Besides evaluating SEC on 16 data sets, we also apply SEC in the application of diagnostic classification of schizophrenia since it has vast application potentiality. Experimental results demonstrate the effectiveness of SEC in both tackling security problem and discriminating schizophrenic patients from healthy controls.

Yuanxin Wu, Jinling Wang, Dewen Hu

Integration of inertial navigation system (INS) and global navigation satellite system (GNSS) is usually implemented in engineering applications by way of Kalman-like filtering. This form of INS/GNSS integration is prone to attitude initialization failure, especially when the host vehicle is moving freely. This paper proposes an online constrained-optimization method to simultaneously estimate the attitude and other related parameters including GNSS antenna's lever arm and inertial sensor biases. This new technique benefits from self-initialization in which no prior attitude or sensor measurement noise information is required. Numerical results are reported to validate its effectiveness and prospect in high accurate INS/GNSS applications.