406 results about "Geometric consistency" patented technology

The invention discloses a three-dimensional Gaussian sputtering scene reconstruction method based on structure perception refined Gaussian, and aims to solve the problems of Gaussian drift, edge blur, structure artifacts and the like of a reconstruction model due to the fact that sparse point cloud contains outliers, Gaussian morphology and normal are mismatched and a multi-dimensional optimization target is lacked in an existing three-dimensional Gaussian sputtering reconstruction method. A key frame is extracted by collecting target scene video data, sparse three-dimensional point clouds are reconstructed by using an SfM algorithm, a depth map and a normal map are generated through a Lotus model, three-dimensional Gaussian distribution is initialized after the sparse point clouds are filtered, a Gaussian covariance matrix is adjusted by using a normal consistency regular term, and the sparse point clouds are extracted. And after structure attribute analysis is carried out, a comprehensive scoring function is constructed to screen Gaussian points, and finally, a combined training framework including luminosity, normal consistency and structure continuity loss is adopted to optimize and generate a three-dimensional Gaussian scene model. The method is mainly applied to the field of three-dimensional reconstruction and multi-view rendering, and scene reconstruction precision and geometric consistency can be improved.

The invention provides a scene reconstruction method based on delayed rendering and three-dimensional Gaussian. The method comprises the following steps: S1, generating initial three-dimensional point cloud data based on a multi-view image; s2, constructing a trainable structural body for three-dimensional Gaussian modeling; s3, normal initialization and residual optimization are carried out on the Gaussian ellipsoid primitives, depth consistency constraint is combined, and a differentiable and learnable normal reconstruction mechanism is realized, so that the geometric expression ability of illumination modeling is enhanced; s4, introducing a reflection training mechanism based on ambient light and a reflection direction, and generating a Gaussian attribute based on a visual angle; and S5, a final image is generated through a differentiable Gaussian sputtering rendering algorithm, and optimization is carried out through pixel loss of the final image and a real image. According to the method, the reality sense and geometric consistency of the Gaussian sputtering model under the complex illumination condition are remarkably improved, and the technical problems of unreal rendering effect, inaccurate surface normal estimation, weak propagation capability and the like of the existing three-dimensional Gaussian sputtering model under the complex illumination condition are solved.

The invention provides a multi-view three-dimensional point cloud reconstruction method and device based on DPE-SE depth estimation, and relates to the technical field of computer vision and three-dimensional reconstruction. The method comprises the following steps: acquiring multi-view image data; preprocessing the image; inputting the preprocessed image into a DPE-SE-based depth estimation model, carrying out key constraint on an edge region through a semantic edge guiding mechanism, carrying out adaptive propagation updating on a weak texture region, realizing accurate depth estimation, and generating a multi-view depth result; then geometric consistency check and multi-scale depth fusion are performed on a multi-view depth result, and a dense depth map is constructed; and finally, performing three-dimensional back projection reconstruction and point cloud optimization processing, and outputting high-quality point cloud data containing three-dimensional coordinates and confidence information. According to the method, the problems of edge mismatching and depth voids are remarkably improved in complex illumination, weak texture and shielding environments, the continuity and structural integrity of the point cloud are improved, and technical support is provided for unmanned aerial vehicle surveying and mapping, building detection and digital twin modeling.

The invention relates to a humanoid robot double-arm body operation method based on reinforcement learning, belongs to the field of robot cooperative control, and is characterized in that a strategy of trajectory block prediction and time integration fusion is used for double-arm cooperative control, and continuity and stability of double-arm operation are improved; in reinforcement learning control, a three-dimensional pose track generation and correction module is introduced, condition generation and denoising correction of a three-dimensional space are carried out on a track block layer, and geometric consistency and naturalness of a generated track are guaranteed; the invention further provides a reinforcement learning optimization framework and a simulation-reality migration process, and through system integration of reward, value guidance and migration processes, strategy deployability and safety are guaranteed; compared with the prior art, the method has the advantages that the naturalness, the collaboration and the success rate of double-arm operation can be remarkably improved, the generalization ability is high, and the good simulation-to-reality migration ability is achieved.

The invention provides a three-dimensional human body posture estimation method and system based on multi-view visual information fusion and a storage medium, and the method comprises the steps: 1, designing the front half part of a model into Ender Layers with the same layer number as a Transform decoder at a multi-view feature fusion layer, carrying out the data enhancement of an input multi-view original image, and carrying out the reconstruction of the Ender Layers in the multi-view feature fusion layer; inputting the CNN Backbone with the shared weight to extract an initial feature map; 2, introducing a micro-reprojection optimization mechanism, deeply fusing the multi-view geometric consistency constraint into a model training process, and guiding the model to predict a three-dimensional attitude end to end; and step 3, constructing a dynamic projection compensation module. The method has the beneficial effects that the method is particularly suitable for capturing human body posture information in a multi-person interaction scene, the shielding problem and depth estimation ambiguity in a single view angle can be effectively overcome, and the robustness, precision and efficiency of three-dimensional human body posture estimation are remarkably improved.

The invention relates to the technical field of electronic component detection, in particular to an IC (integrated circuit) carrier plate detection method based on surface state image extraction, which comprises the following steps: acquiring a gray image, analyzing structural parameters, extracting gradient features, detecting boundary disturbance, integrating the image, calculating an abnormal score, identifying a defect position area, extracting features and outputting an identification result. According to the invention, by analyzing the structure parameters of the bonding pad in the gray level image, calculating the edge line segment, the center coordinate and the spacing, and constructing the two-dimensional coordinate system, the regional positioning reference is enabled to have geometric consistency, the coordinate mapping is combined with the gradient direction change frequency and the continuous aggregation point, the boundary disturbance identification precision is improved, and the image division is executed based on the disturbance region. According to the method, non-functional region mixing is effectively avoided, a clustering and probability model is introduced after region gray level statistics, a deviation scoring mechanism is constructed, gray level feature abnormity is accurately recognized, the discrimination capability of small-amplitude and low-contrast defects is improved, and the selectivity and target focusing performance of feature detection are enhanced.

The invention belongs to the technical field of three-dimensional scene reconstruction, and particularly discloses a multi-view three-dimensional Gaussian densification method and system for adaptive density control, and the method comprises the following steps: collecting a multi-view original image, and carrying out the preprocessing of the multi-view original image; complexity features are extracted, a pixel-level complexity heat map is generated, and a globally unified three-dimensional complexity field is constructed; performing back projection on the reconstruction residual error, high-frequency inconsistency and depth / geometric consistency cost of each view angle, generating three-dimensional error popularity, determining a candidate newly-added set and a candidate pruned set, generating a weak label to train a lightweight multilayer perceptron classifier, outputting a ternary probability corresponding to newly-added / pruned / maintained, and obtaining a new / pruned / maintained three-dimensional perceptron classifier; and performing Gaussian densification operation on the newly added region. By adopting the technical scheme, fine point adding is carried out on the complex area, effective pruning is carried out on the simple area, and meanwhile, the synthesis quality, the global consistency and the calculation efficiency of the new view angle are improved.

The invention discloses an automobile seat framework machining defect detection method based on machine vision, and particularly relates to the technical field of defect detection. The method comprises the following steps: constructing a multi-angle image acquisition and edge reflection modeling module aiming at complex defects such as weld joint pseudo soldering, microcracks, hole site deviation and collapse deformation, extracting weld joint continuity, edge integrity and hole site geometric consistency characteristics by using a deep neural network, and generating a structural feature vector; defect type recognition and credibility scoring are completed through small sample anomaly modeling and Gaussian mixture model classification, sub-pixel-level coordinate labeling of defect positions is achieved in combination with a Gaussian fitting algorithm, a defect positioning map is output, traceability analysis and severity grading are conducted based on historical data comparison, and the defect positioning accuracy is improved. The method is suitable for industrial online detection and quality closed-loop control.

The invention discloses a non-static scene reconstruction method and system based on multi-modal occlusion perception scoring. The method comprises the following steps: generating a geometric consistency distribution diagram, static feature points and geometric prior masks through three-dimensional reconstruction of a multi-view image; fusing the geometric prior mask and a semantic segmentation model to extract a semantic mask and a fused semantic feature map; guiding the image segmentation model to generate candidate masks based on static feature point positive point prompt and occlusion area negative frame prompt, and optimizing the consistency by using a grid complementary fusion method; constructing a multi-modal shielding scoring module, and fusing the multi-source features to output a binary static mask; and utilizing a static mask to constrain neural radiation field training, inhibiting dynamic interference and optimizing static scene reconstruction. According to the method, the static region is sensed cooperatively through multi-modal information, the robustness and accuracy of mask generation are improved, the interference of dynamic elements on neural radiation field modeling is effectively inhibited, and high-quality three-dimensional image reconstruction and new view synthesis of a non-static scene are realized.

The invention belongs to the technical field of three-dimensional scene reconstruction, and particularly provides a shielding object three-dimensional reconstruction method and system based on millimeter wave radar and vision fusion. The method comprises the following steps: acquiring radar point cloud data and visible light image data of a target object; performing space-time alignment on the radar point cloud data and the visible light image data, and establishing a space mapping relation of multi-modal data; generating a three-dimensional geometric structure of the shielded part through a geometric reconstruction model based on three-dimensional space information penetrating through the shielding object in the radar point cloud data; based on the context features of the visible light image data, generating surface textures of the occluded area through a texture completion model; and fusing the three-dimensional geometric structure and the surface texture, and outputting a three-dimensional reconstruction model containing complete information of the occlusion region. Geometric consistency and texture authenticity of virtual-real fusion are guaranteed through space-time alignment and multi-modal data mapping, and the reliability of three-dimensional modeling in a complex shielding scene is remarkably improved.

The invention provides a traffic scene multi-target detection method and system based on deep learning, and relates to the technical field of traffic, and the method comprises the steps: carrying out the semantic prior driven multi-scale feature extraction of a multi-frame image, and carrying out the point-by-point fusion; obtaining a motion field through optical flow estimation and feature similarity calculation, and executing motion compensation to obtain a moving target mask; obtaining a static target boundary by using boundary regression decoupling and geometric consistency constraint; and finally, moving and static target results are combined, and quadratic regression is executed based on consistency evaluation. The dynamic and static targets in the traffic scene can be effectively detected, the boundary regression precision is improved, and the false detection rate caused by shielding is reduced.

The invention discloses a mechanical arm calibration method and system based on multilayer geometric residual modeling, solves the problem that geometric structure information carried by a track is not considered in the mechanical arm calibration process in the prior art, and has the beneficial effect of improving calibration accuracy. According to the specific scheme, the mechanical arm calibration method based on multi-layer geometric residual modeling comprises the steps that the actual position of the tail end of a mechanical arm is obtained in the process that the mechanical arm moves according to a preset track; a continuous preset track is divided into a plurality of track sections with local geometric consistency, the initial theoretical position of the tail end of the mechanical arm is calculated in each track section according to the initial kinematics parameter vector, and multiple types of residual errors are constructed according to the theoretical position of the tail end of the mechanical arm and the obtained actual position of the tail end of the mechanical arm; and obtaining a global parameter increment, and combining the global parameter increment with the initial kinematics parameter vector or the kinematics parameter vector of the previous round to obtain a kinematics parameter vector of a new round of iteration.

The invention discloses a three-dimensional scene reconstruction method and system based on monocular depth estimation, and belongs to the technical field of computer vision and three-dimensional reconstruction, and the method comprises the steps: carrying out the multi-scale feature coding of a monocular RGB image through a mixed attention depth coding module, and obtaining the hierarchical depth feature representation; carrying out autoregression depth decoding through a self-adaptive edge perception depth decoding module to generate an initial depth map; a depth confidence map is calculated through a geometric consistency constraint optimization module and is fed back to a coding module for iterative optimization, and a refined depth map is output; and three-dimensional Gaussian ellipsoid scene representation is constructed through the Gaussian ellipsoid scene reconstruction module. According to the invention, high-precision depth estimation and high-quality three-dimensional reconstruction are realized by constructing a depth-coupled closed-loop cooperative system.

The invention discloses a single view reconstruction and rendering method, which belongs to the field of view reconstruction and rendering, and comprises the following steps of: firstly, generating multi-view feature representation with strong geometric consistency from a single input image by introducing an image diffusion module of a cross attention mechanism; a point cloud reconstruction module with self-attention and cross-attention is utilized, and multi-view information is fused to reconstruct an accurate three-dimensional point cloud; and finally, constructing differentiable three-dimensional Gaussian representation based on the point cloud, rendering the differentiable three-dimensional Gaussian representation, and outputting a new view angle image, a normal map and a depth map. According to the system, a staged training strategy is adopted, and a composite loss function including multi-scale bidirectional consistency smooth loss and feature consistency loss is innovatively used for optimization. According to the method, the problems of low geometric accuracy, multi-view inconsistency, detail missing and the like in single-view reconstruction are effectively solved, and the method can be widely applied to the fields of virtual reality, digital twinning, cultural heritage digitization and the like.

The invention belongs to the technical field of intelligent manufacturing, relates to the directions of numerical control machining, industrial robot trajectory control, complex curved surface path planning and the like, and provides a topology maintenance type curved surface trajectory optimization algorithm fusing surface curvature induction and multi-domain coupling optimization. The method comprises the steps of curved surface preprocessing, initial path construction, multi-domain coupling optimization, topology maintenance, trajectory output and the like. The method comprises the following steps: extracting local curvature characteristics of a free-form surface, adaptively arranging path points, constructing a multi-target optimization model containing indexes such as path uniformity, normal consistency and track fairness, and ensuring that the path direction is consistent with the normal height of the surface through an optimization process. The algorithm adopts an evolutionary optimization strategy to globally adjust the path, and introduces a topology maintenance mechanism to ensure that the original curved surface structure is not damaged in the optimization process. The method is suitable for CNC machining, industrial robot trajectory control and three-dimensional modeling, and has the advantages of being reasonable in path distribution, high in geometric consistency, stable in optimization effect and the like.

The invention discloses an underground pipeline intelligent detection and mapping method based on image recognition, and the method comprises the following steps: 1, obtaining continuous video images, associating feature matching pairs of adjacent key frames, and forming a pose parameter set; 2, inputting the key frame into an improved YOLO-World detection network, and outputting a detection result set; 3, obtaining a geometric consistency matching set according to the detection result set; 4, performing multi-view triangularization on the geometric consistent matching set to form a weight factor; 5, introducing a weight factor, and executing incremental beam adjustment optimization on the pose parameter set and the three-dimensional sparse point set to obtain a sparse semantic point cloud; and step 6, outputting an underground pipe network topology map. According to the invention, high-precision and high-robustness intelligent identification and topological mapping in a complex underground pipeline environment are realized.

The invention provides an injection molding part surface flaw detection method and device based on double-model collaboration, and the method comprises the steps: carrying out the local abnormal reflection feature analysis of a multi-view optical image collected on the surface of an injection molding part based on a first detection model, and obtaining a candidate flaw region; performing spatial positioning in the multi-view optical image based on the candidate flaw area to obtain a multi-view candidate image segment; performing surface geometric continuity analysis on the multi-view candidate image segments based on a second detection model to obtain a three-dimensional surface geometric consistency result; carrying out authenticity discrimination on the candidate flaw area based on a three-dimensional surface geometric consistency result to obtain a real flaw area; wherein the first detection model is used for capturing an optical response model of local abnormal reflection characteristics; the second detection model is a stereoscopic vision model for analyzing the geometric continuity of the multi-view lower surface. According to the invention, the false alarm rate of surface defect detection of the injection molded part under a complex surface condition is reduced.

The invention discloses a dynamic object pose estimation method and system based on multi-ArUco code confidence weighting, and provides a method which does not need a fixed calibration layout, supports random placement of multiple codes, dynamically solves a geometrical relationship between an object and a calibration code, establishes a double confidence mechanism by combining image recognition quality and geometrical consistency, and can estimate the pose of a dynamic object based on multi-ArUco code confidence weighting. And by utilizing multi-frame data fusion, the dynamic target pose can be stably estimated with high precision in complex scenes such as dynamic, inclination, shielding and the like, and accurate positioning in a dynamic environment is realized. The problems that in a dynamic environment, the ArUco code is frequently shielded, the pose is unstable, and the relative relation between the ArUco code and an object is difficult to calibrate are solved.

The invention provides a virtual reality three-dimensional space data correction method, which comprises the following steps of: firstly, acquiring an image, depth and inertia measurement data of a virtual reality terminal, and a pose, a speed and a force feedback signal of an interaction body, and carrying out time sequence alignment under a unified time reference; an interaction event is identified through collision detection, and parameters such as a contact point, a normal direction, a relative speed, a penetration depth and a contact duration are extracted. Then, physical consistency constraints including no penetration, contact stability, friction consistency, momentum conservation and energy non-increase are constructed, and geometric consistency, depth consistency and physical consistency residual functions are established in the local contact area; and solving surface normal, depth, scale, pose, calibration parameters and other corrections through a robust nonlinear optimization method so as to update the point cloud, the grid and the calibration model. According to the method, the consistency and the stability of geometric modeling and physical interaction in the virtual reality scene can be remarkably improved, and the immersion and the interaction precision are improved.

The invention provides a federated learning-based model fusion method and system, and the method comprises the steps: extracting key points and descriptors thereof, generating an initial corresponding relation set, and carrying out the coordinate normalization processing, thereby obtaining a robust basic feature; initializing a federated learning architecture client, performing normalization and cutting preprocessing on local image data, extracting feature descriptors, and training a local model based on a convolutional neural network; aggregating client parameters to obtain a global model, carrying out weighted summation or feature splicing fusion on client feature descriptors, carrying out deep mining on fusion features, and optimizing feature expression in combination with a global context attention mechanism; calculating the inner point probability of the matching pair based on the fusion features, screening a high-probability candidate set, and solving a basic matrix; according to the technical scheme, feature information from different clients can be integrated, the updated global model is used for identifying the matching points of the clients, wrong matching is removed through geometric consistency check, and the matching accuracy is improved.

The invention discloses a virtual space multi-person interaction synchronous control method oriented to an end-cloud collaborative architecture. The invention relates to a computer graphics and three-dimensional modeling technology, and discloses a cross-format lightweight and geometric consistency maintenance method based on a three-dimensional model. Through format-independent geometric representation and a self-adaptive lightweight strategy, efficient compression and precision maintenance of three-dimensional model cross-format conversion are realized. The method specifically comprises the following steps: performing format analysis and geometric feature extraction on an input model, and establishing a unified internal representation; adaptively selecting a multi-level LOD lightweight strategy based on the complexity of the model; the accuracy of key information is ensured through geometric feature keeping and topology consistency detection; the geometric consistency is dynamically maintained by combining error monitoring and an iterative correction mechanism; and generating a target format lightweight model and carrying out quality verification. According to the method, adaptive precision control, multi-level consistency maintenance and format irrelevant processing are combined, the model size and conversion errors are effectively reduced, and cross-platform compatibility and geometric fidelity are improved. The method can be widely applied to the fields of industrial design, game development, virtual reality and the like.

The invention discloses an abdominal CT image multi-view fusion method based on HU physical characteristic guidance, and relates to the technical field of medical image processing. The method comprises the following steps: firstly, constructing a three-dimensional HU volume, generating a semantic mask covering the whole HU range as physical prior, and obtaining two-dimensional slice sequences in the axial direction, the coronal direction and the sagittal direction through three-view projection; on the basis, multi-scale deformable alignment, HU-perceived deformation field fine correction, cross-view attention fusion and regional differentiation decision fusion are sequentially carried out, HU-perceived high-frequency residual enhancement and local contrast self-adaptive processing are carried out on two-dimensional slices, and finally a denser CT slice sequence is generated. According to the method, HU physical partition constraint is introduced in the multi-view alignment and fusion process, abnormal deformation and high-density structure distortion of a gas region are effectively inhibited, and geometric consistency and visual stability of an abdominal CT image in the interpolation reconstruction process are improved.

In a dynamic environment, a visual SLAM (Simultaneous Localization and Mapping) system often causes the problems of large positioning error and inaccurate map construction due to dynamic target interference. In order to improve the robustness and precision of the system, the invention provides a dynamic scene SLAM optimization method based on improved YOLOv11 and geometric consistency constraint. Firstly, ORB features in a scene are extracted, and meanwhile a prior dynamic object and feature points on the prior dynamic object are removed through a YOLOv11 semantic segmentation model; secondly, eliminating feature points on the potential dynamic object by utilizing geometric consistency constraint, and recovering a background shielded by the dynamic object through a semantic perception Gaussian filter; and finally, selecting a high-quality key frame and applying the key frame to loopback detection and global optimization, constructing a basic Gaussian graph through a group of determined poses and point clouds, and finally fusing repair frame information to realize new view rendering and three-dimensional scene optimization.

The invention provides a three-dimensional data generation method and device, and the method comprises the steps: carrying out the planning of a text prompt before generation, optimizing the three-dimensional data in stages, introducing a reflection and correction mechanism in the generation process, recognizing and correcting defects through a multi-modal large model, and introducing a cross-view alignment constraint. And global planning and local fine adjustment of the three-dimensional generation process are realized. According to the method, a complex generation task is decomposed into a closed-loop process of planning-execution-reflection-correction, and multi-view consistency is forced from a feature level, so that geometric consistency and semantic accuracy of generated three-dimensional data can be effectively improved, the problems of structural artifacts and Janus which are easy to occur in the prior art are avoided, and the generation efficiency of the three-dimensional data is improved. And finally, high-quality three-dimensional data with consistent views are generated.

The invention belongs to the technical field of computer vision, and particularly relates to a multi-view image three-dimensional reconstruction method, which comprises the following steps of: firstly, inputting a small amount of two-dimensional images, generating a color point cloud through depth estimation, initializing a three-dimensional Gaussian model, and performing coarse-grained reconstruction by combining luminosity loss and geometric regularization; secondly, planning a camera track based on geometric distribution of the rough model, and collecting a multi-view image sequence; thirdly, performing fine adjustment and repair on the image by using a diffusion model fusing the camera pose and the visual features; and finally, iteratively optimizing the three-dimensional Gaussian model by using the repaired image, and outputting a high-precision three-dimensional reconstruction result. According to the method, high-quality reconstruction can be achieved only through sparse view angle images, and dependence of a traditional method on a large amount of data is broken through. Through composite condition coding and dynamic trajectory optimization, geometric consistency and texture authenticity are effectively improved, artifacts are avoided, and calculation efficiency and reconstruction precision are considered at the same time.

The invention relates to a sparse view angle pose-free scene reconstruction method and system based on 3DGS, belongs to the field of computer vision and three-dimensional reconstruction, and solves the problems of easy failure and poor geometric consistency in a sparse view angle or weak texture environment due to dependence on accurate camera pose priori. Constructing a double-flow sensing module containing semantic flow and geometric flow, extracting semantic features by using a visual basic model, and extracting an explicit geometric corresponding relation by using a dense feature matching network, so as to regress relative camera pose under pose-free priori; a geometric guidance depth refinement module combining a potential diffusion model architecture and Pluecker ray coding is introduced, and scale fuzziness of monocular depth estimation is eliminated through a depth residual prediction mechanism; and based on the micronizable Gaussian rasterization, performing end-to-end optimization by using a self-supervised loss function including rendering consistency, reprojection and epipolar geometric constraint. According to the method, high-fidelity three-dimensional reconstruction is realized without supervision of external parameter true values, and geometric stability and rendering quality in a complex scene are improved.

The invention discloses a concrete crack quantitative detection method and system based on image recognition, and relates to the field of image recognition, firstly, distortion correction and scale calibration are performed through camera calibration, so that the physical authenticity of a quantitative result is ensured, and the problem of inaccurate scale caused by the change of shooting conditions is solved; the method is characterized in that a double-task attention guidance network is constructed, a pixel-level original width graph is generated through direct regression while crack segmentation is carried out, and width calculation errors caused by edge uncertainty in a traditional mode that segmentation is carried out first and then calculation is carried out are fundamentally avoided. Then, geometric consistency correction is carried out on the original width graph by utilizing a segmentation result, and a crack skeleton is extracted, so that the width value is effectively smoothed, and deviation introduced by skeleton deviation is corrected; and finally, based on the skeleton, the corrected width graph and the physical scale conversion factor, realizing high-precision quantification of the geometric index of the crack.

The invention discloses a cross-modal fusion and multi-frequency coding view angle image generation method in an ultra-low orbit scene, and solves the problem of view angle condition generation and single image three-dimensional reconstruction method based on diffusion prior in the ultra-low orbit scene of an aircraft target. Due to insufficient condition information fusion capability, limited radiation or illumination characterization and insufficient cross-view-angle geometric constraint, a problem that a new view angle image with visual coherence and geometric consistency of texture details is difficult to obtain at the same time under large-range view angle and scale change is solved; according to the method, multi-order angle information of direction distribution is effectively captured through perceptual coding of a light direction vector, then the position of a light starting point coordinate is coded, and finally the pose of a camera pose parameter is coded, so that the influence of a relative pose on depth perception and perspective distortion in an image generation process can be depicted; the three coding results are used for a decoding stage of the potential diffusion model, and geometric consistency of detail recovery under a new view angle is effectively improved.

The invention discloses an attention anti-mask double-branch distillation method for three-dimensional point cloud completion. The method comprises the following steps: firstly, extracting a multi-scale space attention map from a teacher model, and generating an anti-mask point cloud based on the multi-scale space attention map; then constructing a double-branch student network, and respectively processing the intermediate feature point cloud and the anti-mask point cloud of the student model; then, a joint recursive distillation module is adopted to carry out recursive upsampling and feature aggregation under geometric consistency constraint on point cloud features of the two student branches and the teacher model; and finally, training a student model by utilizing a triple supervision optimization module and jointly optimizing CD distance loss, characteristic distillation loss and cross-branch contrast loss. According to the invention, the point cloud completion precision and robustness of a student model in a complex automatic driving scene are effectively improved by constructing an anti-mask mechanism guided by teacher attention, introducing a double-input branch architecture, designing a combined recursive distillation mechanism and constructing a triple distillation loss function at the same time.