10 results about "Colored graph" patented technology

The invention relates to the field of three-dimensional reconstruction, in particular to a three-dimensional reconstruction method based on 3D Gaussian and a computer device, and improves the precision of three-dimensional reconstruction. The method comprises the following steps: collecting data, and preprocessing the data to obtain a predicted depth map and a normal map; a color image, a normal image and a depth image are obtained through 3D Gaussian Splitting rendering; respectively subtracting the color picture, the normal graph and the depth graph obtained by rendering from the training truth value, the predicted normal graph and the predicted depth graph to obtain a loss function; the loss function is minimized through stochastic gradient descent, and Gaussian distribution, shape and color are iteratively optimized and trained. The method is suitable for three-dimensional reconstruction.

The invention relates to a depth map super-resolution method based on double-edge consistency constraint, belongs to the field of image quality enhancement, and solves the problem that the generalization ability is reduced due to the fact that the double-edge consistency constraint is not considered and feature fusion of a color map and a depth map is insufficient in an existing depth map super-resolution method. The method comprises the following steps: firstly, converting a depth map super-resolution problem into a three-task optimization model of double-edge consistency constraint, and secondly, according to an alternating direction multiplier method theory, converting the model into an iterative optimization process of color map edge updating, depth map edge updating, depth map updating and augmented Lagrange multiplier updating. Converting the optimization process into an expansion network, embedding a learnable module into an expansion model of an original pure expression to realize high-throughput transmission so as to enhance the expression capability, and further providing a multi-cross attention compensation fusion module; the module realizes approximation of a near-end operator by aggregating a color map edge, a depth map edge, cross-stage features and auxiliary information.

The present disclosure describes systems and methods for assigning nodes in a circuit design to layers. The method includes identifying a plurality of structures in a circuit design. Each of the plurality of structures includes four nodes of the circuit design and each of the four nodes are connected to every other node in the respective structure. The method also includes removing, from the plurality of structures, an even number of pairs of connected nodes of the circuit design to form a reduced node structure and assigning circuit layers for the nodes in the reduced node structure. The method further includes assigning, by a processing device, circuit layers for the pairs of connected nodes removed from the plurality of structures based on the assigned circuit layers for the nodes in the reduced node structure.

The invention discloses a semi-supervised image classification method based on anchor points and adaptive graph learning, belongs to the technical field of traditional machine learning, and provides various and reliable data for semi-supervised image classification by adopting data sets of different scales and types of digital images or color pictures; according to the constructed semi-supervised classification model, prediction sample labels can be converted into prediction anchor point labels through anchor points and a linear propagation mode, then the labels of the samples are obtained through linear combination, and the classification speed is effectively increased through the characteristic that the number of the anchor points is far smaller than the number of the samples; an adaptive graph learning method is adopted to take an adaptive graph as an object of iterative optimization, and the adaptive graph and a sample pseudo-label matrix are learned at the same time, so that the influence of an initial adjacent graph on the classification precision is reduced, and the classification precision is improved.

The invention discloses a honeycomb go chessboard with color grid stickers, and relates to the technical field of sports equipment, each flat-bottom chess groove at the intersection of 361 grid lines of the honeycomb go chessboard is provided with a color grid sticker, the size of the color grid stickers is consistent with that of the chess grooves, chessboard grid lines and color patterns are printed on the color grid stickers, and the 361 color grid stickers integrally form a picture. A user can personally customize the color grid paste patterns of the honeycomb go board, and the go board has the personalized setting function of the user. The color grid stickers can increase the sharpness of the chess grooves on the honeycomb surface of the chessboard, so that a part of disabled people can learn go and play chess with normal people.

The invention relates to a multi-dimensional visualization method and device based on a traditional Chinese medicine acupuncture knowledge graph. The method comprises the following steps: constructing the traditional Chinese medicine acupuncture knowledge graph; performing visual construction on acupuncture points in the traditional Chinese medicine acupuncture knowledge graph and channels and collaterals where the acupuncture points are located in a chart form to form a first color graph; representing pathogenesis and human organs in the traditional Chinese medicine acupuncture knowledge graph in the form of colored graphs and graphs with different shapes to form a second colored graph; and according to syndromes in the traditional Chinese medicine acupuncture knowledge graph, the first color graph and the second color graph, obtaining multi-dimensional visualization graphs of treatment acupoints and syndromes corresponding to different diseases. On the basis of constructing the traditional Chinese medicine acupuncture knowledge graph, a multi-dimensional knowledge visualization method is provided, and the triple relationship of the knowledge graph is displayed through a vivid and visual visualization method according to the implicit knowledge obtained through knowledge graph data exploration according to the relevance between meridians and collaterals and acupuncture points and between syndromes and the acupuncture points. Basic doctors are assisted to systematically understand acupuncture knowledge, and standardization of a traditional Chinese medicine acupuncture treatment system is promoted.

The present invention aims at the multi-scale problem and real-time problem existing in RGB-D semantic segmentation, and proposes an RGB-D multimodal semantic segmentation method. By exchanging the query vectors of color map features and depth map features, a self-attention multimodal information interaction module is designed to realize cross-modal information interaction; and on this basis, a multimodal channel attention correction module and a multimodal global feature aggregation module are designed. After the backbone network downsamples the color map and the depth map, the multimodal channel attention correction module realizes feature correction in the channel dimension, and then the multimodal global feature aggregation module realizes feature aggregation of the corrected features in the spatial dimension, and finally inputs the feature pyramid decoder module for final semantic prediction. The beneficial effects of the present invention are: effectively solving the problem of large differences in target scales in different scenes, effectively improving the accuracy of RGB-D semantic segmentation, and can simultaneously ensure the accuracy and real-time requirements of RGB-D semantic segmentation.

The invention provides a color filling game image click rate prediction model training method, prediction method and equipment, and the method comprises the steps: obtaining each training sample, each training sample comprises color filling game image data of which the total historical click number is higher than a preset threshold value, and multi-modal information, the multi-modal information comprises a line draft graph, a color graph, a text label and a color block graph; training a preset deep learning model to enable the deep learning model to respectively extract feature vectors of the training samples in each iterative training process, splicing the feature vectors to obtain a fused feature vector, and enabling the multi-layer perceptron to output click rate level prediction result data according to the fused feature vector; and performing click rate prediction by taking the deep learning model as a color filling game image click rate prediction model. According to the method, the game experience of the user on the color filling game can be met, the image data of the color filling game can be effectively integrated, and the accuracy of click rate prediction is improved.

The invention discloses a novel texture character creating method and device, equipment and a storage medium. The method comprises the steps that character file data and texture picture data are acquired; forming structural data by the character file data and the texture picture data, and transmitting the structural data into a character rendering engine; in a character rendering engine, mask data are obtained from the character file data through a text shaping engine and a font rendering engine, and a character drawing area is determined; the mask data and the character drawing area are transmitted into a typesetting engine for paragraph layout, and a mask character pattern set is obtained; generating a color mask glyph set by copy construction based on the mask glyph set; setting the texture picture data into texture filling effect attributes of the paintbrush structural body, and configuring a rendering mode of the paintbrush structural body; generating a color image set based on the color mask font set and the configured paintbrush structural body; and rendering and outputting the color image set to obtain texture characters. According to the method, the reusability of textures and characters is enhanced.

The application provides a depth map super-resolution method and system based on entropy map guidance, and belongs to the technical field of computer vision and deep learning; comprising: generating a global entropy guide map according to a low-resolution depth map and a high-resolution color map through an entropy map guidance module; extracting depth features and color features respectively; in a hierarchical direction perception module, decomposing the features into low-frequency and high-frequency components by wavelet decomposition; according to the global entropy guide map, adaptively fusing the components to generate fused depth features; and generating a high-resolution depth map based on the fused depth features. A composite loss function containing a spatial domain loss and an entropy domain loss is used during training; the application adaptively guides by introducing an entropy map, and cooperatively processes high-frequency and low-frequency information by using wavelet decomposition, effectively solving the texture migration error and structure inconsistency problem, and comprehensively improving the quality and realism of the super-resolution depth map.