Although geometric reconstruction of general objects from images has made remarkable progress in recent years, slender structures remain largely underexplored, despite their critical importance in engineering, biomedical, and agricultural applications. To bridge this gap, we propose a dedicated 2DGS-based geometric reconstruction framework tailored for slender structures, achieving accurate and faithful geometry recovery. Our method first addresses the challenge that most slender objects are texture-less, which hinders reliable feature matching and pose estimation in traditional SfM pipelines. By leveraging the curve-like nature of slender structures, we perform a curve-guided SfM process that provides robust camera poses and accurate 3D curve initialization for Gaussian primitives. To ensure SfM reliability, we introduce a high-precision mask extraction strategy that integrates geometric priors with a segmentation network, effectively handling self-occlusion and thin geometry. Furthermore, to enhance fine geometric recovery, we incorporate a differentiable Poisson reconstruction module to extract an initial mesh during training, which is then refined via image-space iterative optimization using differentiable mesh rasterization. In contrast to conventional approaches that rely on differentiable Gaussian rasterization followed by TSDF-based mesh extraction, our method avoids the additional geometric errors and artifacts introduced during the intermediate TSDF conversion, thereby improving the overall reconstruction quality. Comprehensive experiments on both synthetic and real-world datasets validate that our method achieves superior reconstruction quality compared to state-of-the-art approaches.

Recently, patch deformation-based methods have demonstrated significant effectiveness in multi-view stereo due to their incorporation of deformable and expandable perception for reconstructing textureless areas. However, these methods generally focus on identifying reliable pixel correlations to mitigate matching ambiguity of patch deformation, while neglecting the deformation instability caused by edge-skipping and visibility occlusions, which may cause potential estimation deviations. To address these issues, we propose DVP-MVS++, an innovative approach that synergizes both depth-normal-edge aligned and harmonized cross-view priors for robust and visibility-aware patch deformation. Specifically, to avoid edge-skipping, we first apply DepthPro, Metric3Dv2 and Roberts operator to generate coarse depth maps, normal maps and edge maps, respectively. These maps are then aligned via an erosion-dilation strategy to produce fine-grained homogeneous boundaries for facilitating robust patch deformation. Moreover, we reformulate view selection weights as visibility maps, and then implement both an enhanced cross-view depth reprojection and an area-maximization strategy to help reliably restore visible areas and effectively balance deformed patch. Additionally, we obtain geometry consistency by adopting both aggregated normals via view selection and projection depth differences via epipolar lines, and then employ SHIQ for highlight correction to facilitate highlight perception capacity, thus improving reconstruction quality during propagation and refinement stage. Evaluations on ETH3D, Tanks & Temples and Strecha datasets exhibit the state-of-the-art performance and robust generalization capability of our proposed method.

Patch deformation-based methods have recently exhibited substantial effectiveness in multi-view stereo, due to the incorporation of deformable and expandable perception to reconstruct textureless areas. However, such approaches typically focus on exploring correlative reliable pixels to alleviate match ambiguity during patch deformation, but ignore the deformation instability caused by mistaken edge-skipping and visibility occlusion, leading to potential estimation deviation. To remedy the above issues, we propose DVP-MVS, which innovatively synergizes depth-edge aligned and cross-view prior for robust and visibility-aware patch deformation. Specifically, to avoid unexpected edge-skipping, we first utilize Depth Anything V2 followed by the Roberts operator to initialize coarse depth and edge maps respectively, both of which are further aligned through an erosion-dilation strategy to generate fine-grained homogeneous boundaries for guiding patch deformation. In addition, we reform view selection weights as visibility maps and restore visible areas by cross-view depth reprojection, then regard them as cross-view prior to facilitate visibility-aware patch deformation. Finally, we improve propagation and refinement with multi-view geometry consistency by introducing aggregated visible hemispherical normals based on view selection and local projection depth differences based on epipolar lines, respectively. Extensive evaluations on ETH3D and Tanks & Temples benchmarks demonstrate that our method can achieve state-of-the-art performance with excellent robustness and generalization.

Recently, patch deformation-based methods have demonstrated significant strength in multi-view stereo by adaptively expanding the reception field of patches to help reconstruct textureless areas. However, such methods mainly concentrate on searching for pixels without matching ambiguity (i.e., reliable pixels) when constructing deformed patches, while neglecting the deformation instability caused by unexpected edge-skipping, resulting in potential matching distortions. Addressing this, we propose MSP-MVS, a method introducing multi-granularity segmentation prior for edge-confined patch deformation. Specifically, to avoid unexpected edge-skipping, we first aggregate and further refine multi-granularity depth edges gained from Semantic-SAM as prior to guide patch deformation within depth-continuous (i.e., homogeneous) areas. Moreover, to address attention imbalance caused by edge-confined patch deformation, we implement adaptive equidistribution and disassemble-clustering of correlative reliable pixels (i.e., anchors), thereby promoting attention-consistent patch deformation. Finally, to prevent deformed patches from falling into local-minimum matching costs caused by the fixed sampling pattern, we introduce disparity-sampling synergistic 3D optimization to help identify global-minimum matching costs. Evaluations on ETH3D and Tanks & Temples benchmarks prove our method obtains state-of-the-art performance with remarkable generalization.

Abstract Reconstructing underwater object geometry from multi‐view images is a long‐standing challenge in computer graphics, primarily due to image degradation caused by underwater scattering, blur, and color shift. These degradations severely impair feature extraction and multi‐view consistency. Existing methods typically rely on pre‐trained image enhancement models as a preprocessing step, but often struggle with robustness under varying water conditions. To overcome these limitations, we propose WaterGS, a novel framework for underwater surface reconstruction that jointly recovers accurate 3D geometry and restores true object colors. The core of our approach lies in introducing a Physically‐Based imaging model into the rendering process of 2D Gaussian Splatting. This enables accurate separation of true object colors from water‐induced distortions, thereby facilitating more robust photometric alignment and denser geometric reconstruction across views. Building upon this improved photometric consistency, we further introduce a Gaussian bundle adjustment scheme guided by our physical model to jointly optimize camera poses and geometry, enhancing reconstruction accuracy. Extensive experiments on synthetic and real‐world datasets show that WaterGS achieves robust, high‐fidelity reconstruction directly from raw underwater images, outperforming prior approaches in both geometric accuracy and visual consistency.

This paper surveys the technology used in three-dimensional indoor scene geometry estimation from a single 360° omnidirectional image, which is pivotal in extracting 3D structural information from indoor environments. The technology transforms omnidirectional data into a 3D model, depicting spatial structure, object positions, and scene layout. Its significance spans various domains, including virtual reality (VR), augmented reality (AR), mixed reality (MR), game development, urban planning, and robot navigation. We begin by revisiting foundational concepts of omnidirectional imaging and detailing the problems, applications, and challenges in this field. Our review categorizes the fundamental tasks of structure recovery, depth estimation, and layout recovery. We also review pertinent datasets and evaluation metrics, providing the latest research as a reference. Finally, we summarize the field and discuss potential future trends to inform and guide further research.

Grasping is a basic but challenging task in intelligent robotic manipulation, and grasping pose detection is the key in this task. Most current work is shifting from 2D planar grasping to more flexible six-degree-of-freedom (6-DoF) grasping, and some significant progress has been made. However, there are still limitations such as low success rate and poor robustness in cluttered scenes. In this paper, we investigate 6-DoF grasping in cluttered scenes, and propose a cascaded multitarget learning network based on self-attention mechanism and multiscale sampling. The self-attention mechanism effectively improves the network’s attention to the correct grasping pose, while multiscale sampling improves the network’s adaptability to grasping objects of different sizes. In addition, we propose a dual-objective evaluation metric based on the force-closure metric and the center-of-mass distance metric, which can make a more reasonable and reliable evaluation of the grasping poses in the dataset. Our model is evaluated on large-scale benchmarks as well as the real robot system. The proposed method achieves state-of-the-art results on GraspNet-1Billion (8.8+AP), and shows 95.24% success rates in real cluttered scenes.

Recently, patch-deformation methods have exhibited significant effectiveness in multi-view stereo owing to the deformable and expandable patches in reconstructing textureless areas. However, existing approaches neglect to address the problem of deformation instability caused by easily overlooked edge-skipping, potentially leading to matching distortions, thus leaving room for further improvement. To fill this gap, we propose SED-MVS, which adopts panoptic segmentation and multi-trajectory diffusion strategy for segmentation-driven and edge-aligned patch deformation. Specifically, to prevent unanticipated edge-skipping, we first employ SAM2 for panoptic segmentation as depth-edge guidance to guide patch deformation, followed by multi-trajectory diffusion strategy to ensure patches are comprehensively aligned with depth edges. Moreover, to avoid potential inaccuracy of random initialization, we combine both sparse points from LoFTR and monocular depth map from DepthAnything V2 to restore reliable and realistic depth map for initialization and supervised guidance. Finally, we integrate the segmentation image with the monocular depth map to exploit inter-instance occlusion relationship, then further regard them as occlusion map to implement two distinct edge constraint, thereby facilitating occlusion-aware patch deformation. Extensive results on ETH3D, Tanks & Temples, BlendedMVS, Strecha and DL3DV-10K datasets validate the state-of-the-art performance and robust generalization capability of our proposed method.

In this paper, we introduce Segmentation-Driven Deformation Multi-View Stereo (SD-MVS), a method that can effectively tackle challenges in 3D reconstruction of textureless areas. We are the first to adopt the Segment Anything Model (SAM) to distinguish semantic instances in scenes and further leverage these constraints for pixelwise patch deformation on both matching cost and propagation. Concurrently, we propose a unique refinement strategy that combines spherical coordinates and gradient descent on normals and pixelwise search interval on depths, significantly improving the completeness of reconstructed 3D model. Furthermore, we adopt the Expectation-Maximization (EM) algorithm to alternately optimize the aggregate matching cost and hyperparameters, effectively mitigating the problem of parameters being excessively dependent on empirical tuning. Evaluations on the ETH3D high-resolution multi-view stereo benchmark and the Tanks and Temples dataset demonstrate that our method can achieve state-of-the-art results with less time consumption.

As an important area of machine learning, re-inforcement learning has specific applicability in multi-agent systems (including UAV swarms). In this article, we use re-inforcement learning algorithm (i.e., the QMIX algorithm) to resolve the problem of UAV swarm confrontation, considering the condition of asymmetric confrontation under which the adversary's combat power is much stronger than our own. First, after constructing the system model, we develop the QMIX algorithm by designing the state space, action space, and reward function. Second, we propose a confrontation strategy that integrates decisions made by the QMIX algorithm and the artificial potential field method for UAV swarm confrontation. Finally, the experimental results show that our proposed confrontation strategy has a 72% higher win rate compared to the QMIX algorithm under asymmetric confrontation conditions.

Pan-Tilt-Zoom (PTZ) camera networks are pervasive in many applications, such as video surveillance, sports analysis and epidemic prevention. However, it is difficult to control several PTZ cameras observing a large scene due to the high complexity of PTZ camera networks. This problem, called the coverage control for PTZ cameras, draws broad attention of researchers. Virtual potential field (VPF) can enhance the coverage performance and reduce the overlap region of cameras, but it does not fully take the actual scenario into account. In this work, we introduce scene potential map (SPM) to the VPF method, investigating both the scene and the task in the optimization. The proposed scene potential map characterizes the importance of target region and evaluates the perception quality of PTZ camera. Then we propose a novel virtual force analysis method to optimalize poses of the PTZ camera network. We also develop a region partition method based on the perception quality measure to divide the target region and achieve better zoom level, realizing an excellent coverage performance of PTZ camera networks. Finally, the evaluation experiments clearly demonstrated that our proposed coverage control scheme can achieve remarkably better performance than state-of-the-arts.

Visual odometry, which aims to estimate relative camera motion between sequential video frames, has been widely used in the fields of augmented reality, virtual reality, and autonomous driving. However, it is still quite challenging for state-of-the-art approaches to handle low-texture scenes. In this paper, we propose a robust and efficient visual odometry algorithm that directly utilizes edge pixels to track camera pose. In contrast to direct methods, we choose reprojection error to construct the optimization energy, which can effectively cope with illumination changes. The distance transform map built upon edge detection for each frame is used to improve tracking efficiency. A novel weighted edge alignment method together with sliding window optimization is proposed to further improve the accuracy. Experiments on public datasets show that the method is comparable to state-of-the-art methods in terms of tracking accuracy, while being faster and more robust.

Abstract Fish morphology is an essential basis for fishery management, as it can reflect the growth status of fishes. Noncontact 3D reconstruction of underwater fish is a new way to obtain fish morphology. While it is difficult to reconstruct fish on account of the inadequate information caused by fish swimming and poor underwater imaging. This article introduces a morphable fish modeling method for the underwater binocular vision system. First, we define a fish representation based on selected landmarks. Then, we propose a chirality‐supervision incorporated hourglass network to estimate fish orientation and fish 2D landmarks simultaneously, and calculate fish 3D landmarks by triangulation. Next, we propose a fish modeling method which is based on 3D landmarks and introduce the optimization procedure of fish modeling. Finally, we obtain the complete 3D fish model corresponding to the input images. To train our network and build a parametric model, we constructed an underwater vision dataset and fish instance dataset respectively. We conducted experiments with grass carp as an example, and the experimental results show that our method can achieve effective fish modeling and is useful for noncontact measurement of underwater fish.

Omnidirectional images of 180° or 360° field of view provide the entire visual content around the capture cameras, giving rise to more sophisticated scene understanding and reasoning and bringing broad application prospects for VR/AR/MR. As a result, researches on omnidirectional image layout estimation have sprung up in recent years. However, existing layout estimation methods designed for panorama images cannot perform well on fisheye images, mainly due to lack of public fisheye dataset as well as the significantly differences in the positions and degree of distortions caused by different projection models. To fill theses gaps, in this work we first reuse the released large-scale panorama datasets and reproduce them to fisheye images via projection conversion, thereby circumventing the challenge of obtaining high-quality fisheye datasets with ground truth layout annotations. Then, we propose a distortion-aware module according to the distortion of the orthographic projection (i.e., OrthConv) to perform effective features extraction from fisheye images. Additionally, we exploit bidirectional LSTM with two-dimensional step mode for horizontal and vertical prediction to capture the long-range geometric pattern of the object for the global coherent predictions even with occlusion and cluttered scenes. We extensively evaluate our deformable convolution for room layout estimation task. In comparison with state-of-the-art approaches, our approach produces considerable performance gains in real-world dataset as well as in synthetic dataset. This technology provides high-efficiency and low-cost technical implementations for VR house viewing and MR video surveillance. We present an MR-based building video surveillance scene equipped with nine fisheye lens can achieve an immersive hybrid display experience, which can be used for intelligent building management in the future.

Monocular depth estimation is a challenging problem in computer vision and is crucial for understanding 3D scene geometry. Recently, deep convolutional neural networks (DCNNs) based methods have improved the estimation accuracy significantly. However, existing methods fail to consider complex textures and geometries in scenes, thereby resulting in loss of local details, distorted object boundaries, and blurry reconstruction. In this paper, we proposed an end-to-end multi-scale residual pyramid attention network (MRPAN) to mitigate these problems. First, we propose a multi-scale attention context aggregation (MACA) module, which consists of spatial attention module (SAM) and global attention module (GAM). By considering the position and scale correlation of pixels from spatial and global perspectives, the proposed module can adaptively learn the similarity between pixels so as to obtain more global context information of the image and recover complex structures in the scene. Then we proposed an improved residual refinement module (RRM) to further refine the scene structure, giving rise to deeper semantic information and retain more local details. Experimental results show that our method achieves more promising performance in object boundaries and local details compared with other state-of-the-art methods.

Albeit remarkable progress has been made to improve the accuracy and completeness of multi-view stereo (MVS), existing methods still suffer from either sparse reconstructions of low-textured surfaces or heavy computational burden. In this paper, we propose a Confidence-based Large-scale Dense Multi-view Stereo (CLD-MVS) method for high resolution imagery. Firstly, we formulate MVS as a multi-view depth estimation problem, and employ a normal-aware efficient PatchMatch stereo to estimate the initial depth and normal map for each reference view. A self-supervised deep learning method is then developed to predict the spatial confidence for multi-view depth maps, which is combined with cross-view consistency to generate the ground control points. Subsequently, a confidence-driven and boundary-aware interpolation scheme using static and dynamic guidance is adopted to synthesize dense depth and normal maps. Finally, a refinement procedure which leverages synthesized depth and normal as prior is conducted to estimate cross-view consistent surface. Experiments show that the proposed CLD-MVS method achieves high geometric completeness while preserving fine-scale details. In particular, it has ranked No. 1 on the ETH3D high-resolution MVS benchmark in terms of F1-score.

Human trajectory prediction is challenging and critical in various applications (e.g., autonomous vehicles and social robots). Because of the continuity and foresight of the pedestrian movements, the moving pedestrians in crowded spaces will consider both spatial and temporal interactions to avoid future collisions. However, most of the existing methods ignore the temporal correlations of interactions with other pedestrians involved in a scene. In this work, we propose a Spatial-Temporal Graph Attention network (STGAT), based on a sequence-to-sequence architecture to predict future trajectories of pedestrians. Besides the spatial interactions captured by the graph attention mechanism at each time-step, we adopt an extra LSTM to encode the temporal correlations of interactions. Through comparisons with state-of-the-art methods, our model achieves superior performance on two publicly available crowd datasets (ETH and UCY) and produces more "socially" plausible trajectories for pedestrians.

Software defined network (SDN)can manage the whole network flexibly because of its programmability and logically centralized architecture. However, the centralized architecture of SDN makes it more vulnerable to Denial of Service (DoS)attack which is launched by sending a large number of malicious packet_in packets to consume the resources of the controller and data planes. In order to protect the normal operation of the network from DoS, we propose an effective DoS mitigation framework based on non-cooperative repeated game called PrioGuard. DoS can be detected based on the information entropy, packet_in rate and packet_in response rate. Furthermore, the penalty-incentive mechanism of repeated game is adopted to punish these attackers by lowering their priority in order to postpone their requests. The requests from attackers will be migrated to data plane cache, which can mitigate the interface cache of control plane and make the controller process the normal requests effectively. We have implemented a prototype system of PrioGuard. Simulation evaluations demonstrate that our scheme is very effective with less response time, less packet loss rate and lower controller load.

Accurate recovery of 3D geometrical surfaces from calibrated 2D multi-view images is a fundamental yet active research area in computer vision. Despite the steady progress in multi-view stereo (MVS) reconstruction, many existing methods are still limited in recovering fine-scale details and sharp features while suppressing noises, and may fail in reconstructing regions with less textures. To address these limitations, this paper presents a detail-preserving and content-aware variational (DCV) MVS method, which reconstructs the 3D surface by alternating between reprojection error minimization and mesh denoising. In reprojection error minimization, we propose a novel inter-image similarity measure, which is effective to preserve fine-scale details of the reconstructed surface and builds a connection between guided image filtering and image registration. In mesh denoising, we propose a content-aware ℓp-minimization algorithm by adaptively estimating the p value and regularization parameters. Compared with conventional isotropic mesh smoothing approaches, the proposed method is much more promising in suppressing noise while preserving sharp features. Experimental results on benchmark data sets demonstrate that our DCV method is capable of recovering more surface details, and obtains cleaner and more accurate reconstructions than the state-of-the-art methods. In particular, our method achieves the best results among all published methods on the Middlebury dino ring and dino sparse data sets in terms of both completeness and accuracy.

Recent years have seen a rapid growth in the number of virtual machines and virtual machine images that are managed to support infrastructure as a service (IaaS). For example, Amazon Elastic Compute Cloud (EC2) has 6,521 public virtual machine images. This creates several challenges in management of image files in a cloud computing environment. In particular, a large amount of duplicate data that exists in image files consumes significant storage space. To address this problem, we propose an effective image file storage technique using data deduplication with a modified fixed-size block scheme. When a user requests to store an image file, this technique first calculates the fingerprint for the image file, and then compares the fingerprint with the fingerprints in a fingerprint library. If the fingerprint of the image is already in the library, a pointer to the existing fingerprint is used to store this image. Otherwise this image will be processed using the fixed-size block image segmentation method. We design a metadata format for image files to organize image file blocks and a new MD5 index table of image files to reduce their retrieval time. The experiments show that our technique can significantly reduce the transmission time of image files that have already existed in storage. Also the deletion rate for image groups which have the same version of operating systems but different versions of software applications is up about 58%.