12 results about "Visual Disparity" patented technology

This application belongs to the field of virtual art restoration technology, specifically providing a deep learning-based virtual art restoration system. The system primarily analyzes historical images and environmental data of the artifact and restoration materials to train an aging prediction model and simulate long-term appearance changes. By quantitatively comparing the differences and stability of their aging trajectories, it calculates the long-term compatibility score for each restoration material and automatically selects the optimal material to generate the final virtual restoration image. This application effectively solves the problem in existing technologies where it is difficult to predict significant visual differences that may appear between restoration materials and the artifact itself after long-term natural aging, ultimately leading to insufficient durability of the restoration results. It achieves scientific prediction and optimized selection of the long-term visual compatibility of restoration schemes, significantly improving the reliability and stability of restoration results and reducing the risk of restoration failure due to material aging incompatibility.

This application relates to a method for identifying wildfire hazards based on a spatial-temporal correlation operator using visual language priors. The aim is to address the problems of high false alarm rates and difficulty in early identification of concealed fires in vision-based power transmission line wildfire monitoring methods under complex backgrounds. The method constructs a multimodal fusion tensor for the current frame based on visible light and infrared images of the target area. It then uses a visual language prior module to extract features from the multimodal fusion tensor and meteorological data to obtain semantic feature vectors and semantic credibility. Finally, it uses a spatial-temporal correlation module to obtain a spatial-temporal evolution feature vector based on the multimodal fusion tensor, historical time-series cache queue, binocular disparity map, and the semantic credibility. Finally, it uses a spatial-temporal correlation operator to fuse the semantic feature vector, the semantic credibility, and the spatial-temporal evolution feature vector to obtain the probability of wildfire hazard risk.

This application discloses a disparity correction method, apparatus, electronic device, storage medium, and product. The method includes: determining an initial disparity map between a left and right image acquired by a binocular camera based on a binocular matching disparity network; determining matching pixel pairs between the left and right images based on the initial disparity map; for each matching pixel pair, traversing all disparities within the disparity neighborhood centered on the initial disparity corresponding to the matching pixel pair, and calculating the aggregation cost of the target pixel within a preset-sized pixel window in its target image based on the current disparity; determining the target disparity corresponding to the target pixel based on the aggregation cost corresponding to each disparity in the disparity neighborhood, and correcting the corresponding initial disparity in the initial disparity map based on the target disparity to generate a target disparity map. This solution not only effectively ensures the robustness of deep learning-based matching disparity but also improves the accuracy of binocular visual disparity.

The application provides a road surface reconstruction method based on a direction perception pseudo binocular network, comprising a direction perception feature enhancement module: by combining road geometric features with view angle changes, multiple feature enhancement mechanisms such as a spatial saliency perception unit and an internal direction decoupling module are adopted, so that the network can effectively enhance the perception ability of the road surface geometry; a pseudo binocular cost volume construction operator is proposed: by introducing feature difference modeling and a nonlinear gating mechanism, the parallax effect in binocular vision is simulated, and a pseudo binocular disparity volume is efficiently constructed under the condition of monocular input. Therefore, the application first realizes high-precision and high-robustness three-dimensional road reconstruction under the condition of monocular input, and the innovation lies in the introduction of direction perception and pseudo binocular disparity modeling technology, which is especially suitable for complex and variable road scenes. In practical applications, the technology can be widely used in the fields of automatic driving, high-precision map construction and the like, and has wide market prospects and technical value.

The application provides a display module, a backlight module of the display module comprises a backboard, the backboard comprises a bottom, a side and a first bending part, the side forms a containing cavity around the bottom, and the first bending part is connected to an end of the side away from the bottom; a display panel is arranged on a light emitting side of the backlight module and corresponds to the containing cavity, the display panel comprises array substrates and a color film substrate arranged oppositely, and a first polaroid arranged on a side of the color film substrate away from the array substrate, the first polaroid is arranged inwardly, and the color film substrate oppositely forms a first protruding part protruding from the first polaroid; a front frame is arranged on a side of the first protruding part away from the array substrate and is fixedly connected with the first bending part, and an extension direction of the first bending part is different from an extension direction of the side; in this way, by arranging the first bending part with the different extension direction on the backboard and fixedly connecting the front frame with the first bending part, the problem of obvious visual difference existing in the current visual four-side frameless design is improved.

This invention belongs to the field of image processing technology and specifically discloses a generalized stereo matching method and device based on structure and motion cues. It includes: aligning image features based on disparity information to generate confidence information; fusing binocular disparity information and monocular depth information according to the confidence information to obtain an initial fused disparity map; aligning binocular image features based on the initial fused disparity map; and initializing the hidden state during the iteration process. During the iteration process, structural cues are constructed based on the geometric consistency information between the current disparity and monocular depth, and motion cues are constructed by combining the cost information obtained during stereo matching. The hidden state is recursively updated accordingly, and the disparity is progressively corrected, outputting the final disparity map. This invention effectively improves the zero-shot generalization ability of stereo matching methods under unknown scenes and cross-dataset conditions, and reduces the dependence on large-scale labeled data and scene-specific training.

This invention relates to a medical image report generation method based on a dual-image encoder, comprising: acquiring a current chest X-ray image and historical chest X-ray images; inputting the current chest X-ray image and historical chest X-ray images into a medical image report generation model to obtain radiology report text corresponding to the current chest X-ray image; wherein, the medical image report generation model includes: a single-modal encoding module for extracting image features of the current chest X-ray image and historical chest X-ray images, as well as text features of the radiology report text; a cross-modal encoding module for performing cross-modal fusion of the image features and text features to obtain multimodal features incorporating visual difference information; and a text decoding module for generating the radiology report text corresponding to the current chest X-ray image based on the multimodal features incorporating visual difference information. This invention enables the modeling of image difference information and the generation of corresponding radiology reports.

This invention discloses a method and apparatus for seamless handwriting rendering based on visual error closed-loop control. The method includes: obtaining a visual difference function by weighted calculation based on the absolute difference of pixel visual feature data in the device; calculating a correction intensity factor based on the visual difference function and the user's writing speed; if the correction intensity factor is greater than zero and the user's writing speed is less than a preset writing speed threshold, then updating the region with the largest visual difference function in the interactive device according to the target pixel attributes. This invention proposes a method and apparatus for seamless handwriting rendering based on visual error closed-loop control. In low-speed writing scenarios where perceptible visual differences exist and users are sensitive to flicker, it specifically updates the region with the most significant differences, achieving pixel-level precise adaptation. This eliminates visual jumps and flicker in dual-layer rendering, solving the problem of visual jumps and flicker caused by pixel visual differences between the preview layer and the final layer in existing dual-layer rendering.

The application provides an image processing method, device and equipment, the method comprising: obtaining a first original image and a second original image corresponding to a target object; obtaining a first disparity image by using a deep learning algorithm based on the first original image and the second original image; obtaining a second disparity image by using a target binocular algorithm based on the first original image and the second original image; fusing the first disparity image and the second disparity image to obtain a target disparity image; and generating a depth image corresponding to the target object based on the target disparity image. Through the technical scheme of the application, the disparity image of the deep learning algorithm and the disparity image of the target binocular algorithm are fused to obtain a high-precision noise-free target disparity image for distance measurement, and the advantages of the deep learning algorithm and the target binocular algorithm in binocular disparity estimation are fully utilized.