6 results about "Light field rendering" patented technology

A method for light field rendering includes: obtaining an n-dimensional mixture model, with n a natural number equal to or larger than 4, of a light field. The model is made of kernels wherein each kernel represents light information and is expressed by parameter values; mathematically reducing the n-dimensional mixture model into a 2-dimensional mixture model of an image given a certain point of view, wherein the 2-dimensional model is also made of kernels; rendering a view in a pixel domain from the 2-dimensional model made of kernels.

The application discloses an immersion interactive method and device for appreciating artifacts, and relates to the technical field of human-computer interaction. The method comprises the following steps: in an immersive digital experience cabin, the three-dimensional coordinates of the user's double pupils and the hand skeleton node coordinates are collected, the gesture instruction is analyzed, and the three-dimensional space viewpoint parameter set of the next moment is predicted; in a virtual engine scene, the UV texture coordinates are obtained by ray intersection, the three-dimensional region of interest is demarcated, the candidate tile set and the tile topology feature matrix are retrieved and generated; based on the pre-constructed fitness function, the improved tornado optimization algorithm is used for solving, and the global optimal tile loading sequence is output; the naked-eye light field rendering and the three-dimensional space multi-modal superposition are performed on the global optimal tile loading sequence, and the fusion picture of the artifacts and the suspended interpretation is presented on the naked-eye 3D cabin screen. The application solves the problems of viewpoint prediction lag, texture tile loading leading to video memory overflow or picture damage, and lack of spatial multi-modal fusion in the prior art.

The invention discloses a GPU acceleration light field image generation method based on Image3DModel, and belongs to the technical field of 3D generation and light field rendering. The method comprises the following steps: preprocessing an input single target image to generate a standardized image prompt; inputting into an Image3DModel multi-view diffusion model, optimizing to obtain a three-dimensional neural radiation field model NeRF, and taking a parameter set of the three-dimensional neural radiation field model NeRF as an intermediate representation of a 3D model; through GPU large-scale parallel volume rendering, a 4D light field data array is generated and optimized; and based on a specified target view angle request, performing interpolation calculation on the 4D light field data array through a light field interpolation engine, and outputting a high-resolution light field image after super-resolution processing. According to the invention, through deep fusion of an advanced generation model and an efficient calculation architecture, a high-quality and geometrically consistent light field image is directly generated from a single image prompt.

The application provides a multi-modal CT image data fusion three-dimensional reconstruction method for puncture positioning, constructs a high-dimensional feature space containing anatomical structure, metabolic activity and time-varying information through characteristic coding of spiral CT and multi-phase PET data; realizes modality alignment by using a mutual information driven double constraint registration mechanism, and completes cognitive level fusion of cross-modal features by combining a dynamic weight tensor of patient physiological characteristics, clinical requirements and organ semantics; and finally generates a three-dimensional reconstruction model with medical accuracy and clinical guidance by adaptive light field rendering and topology preservation optimization, so as to provide precise visualization support for puncture surgery.

The invention relates to the technical field of three-dimensional display, and discloses a method for dynamically adjusting a picture according to a viewing condition based on self-adaptive naked-eye 3D, and the method comprises the following steps: obtaining a current viewer state of a viewer; on the basis of the state and the rendering confidence map of the previous period, predicting and generating a prediction viewpoint of the next moment by fusing scene significance analysis and confidence feedback weighted correction; based on the predicted viewpoint, left and right eye images are generated through neural light field rendering, and a current period rendering confidence map representing the rendering quality is synchronously generated; and finally, based on the generated image and the current period rendering confidence map, adaptive optical compensation and display are carried out through an active microlens array. According to the method, a closed-loop system from intention prediction to rendering quality feedback to optical compensation is constructed, so that active and forward-looking response to viewing condition changes is realized, and the smoothness, the stability and the perception image quality of naked eye 3D display are remarkably improved.

Systems and methods for fast light field rendering from a three-dimensional (3D) representation of a scene. In at least one embodiment, fast light field rendering exploits cached color values of a plurality of color planes corresponding to a reference view and cached transmittance values of a plurality of transmittance planes corresponding to the reference view to composite a light field quilt via a single sweep through a plurality of sampling planes / volume chunks, thereby enhancing computational efficiency during rendering.