Adaptive clothes animation modeling method based on visual perception

Abstract

The invention discloses an adaptive clothes modeling method based on visual perception. The method comprises the steps of 1, constructing a clothes visual saliency model which accords with a human eye characteristic, applying deep convolutional neural network learning and extracting different hierarchical abstract characteristics of each image frame of clothes animation, and performing deep learning on the characteristics and true eye motion data for obtaining a visual saliency model; 2, performing clothes sub-area modeling, based on the visual saliency model which is constructed in the step 1, predicating a visual saliency chart of a clothes animation image, extracting attention degree of a clothes area, filtering clothes deformation, and performing sub-area modeling through setting a detail simulation factor according to camera viewpoint motion information and physical deformation information; and 3, constructing an adaptive clothes model driven by visual perception and realizing simulation, and realizing clothes sub-area modeling by means of adaptive multi-precision grid technology, performing high-precision modeling on the area with high detail simulation factor, and performing low-precision modeling on the area with low detail simulation factor, and performing dynamics calculation and bumping detection based on the steps above, and constructing a visual vivid clothes animation system.

Description

technical field [0001] The invention belongs to the technical field of virtual reality and computer graphics, and in particular relates to an adaptive clothing animation modeling method based on visual perception. Background technique [0002] The visual fidelity of clothing animation simulation effect has always been the goal that researchers are working on. In order to obtain delicate clothing effects, high-precision modeling of clothing models is usually required to express its rich deformation details. However, the high-precision model has nearly 10,000 primitives, which requires a large number of collision detection and large-scale dynamic equation solving, resulting in high computational costs and reduced system performance. [0003] In order to solve the above problems, an effective solution is to carry out adaptive multi-precision modeling on clothing. The existing methods mainly include: modeling method based on deformation state drive, that is, to estimate the pos...

AI Technical Summary

Problems solved by technology

[0004] However, the common problem existing in the existing methods is that when modeling animation, only the objective reality of clothing movement is considered, and the influence of the subjective effect of the human eye on the perceived realism is completely ignored.

Therefore, the human visual system’s perception of the deformation of different regions of clothing will be affected by many factors; if we simply consider building a physically realistic animation model or improving the accuracy of the clothing model, and completely ignore the impact of visual sensitivity on perceived authenticity, then It is difficult to guarantee the visual fidelity of the final generated clothing animation

Images