Object model determination method and related device

Abstract

The embodiment of the invention discloses an object model determination method and a related device, after a non-parameterized model is obtained by scanning a target three-dimensional object, model vertex expansion is carried out by using an initial parameterized model with driving parameters so as to obtain a registered three-dimensional model with the model vertex number close to that of the non-parameterized model. The method comprises the following steps of: performing attitude alignment to obtain an aligned three-dimensional model, enabling the aligned three-dimensional model and a non-parameterized model to be in the same attitude, determining a model vertex offset parameter relative to the non-parameterized model, and adjusting the aligned three-dimensional model based on the model vertex offset parameter to obtain a non-parameterized three-dimensional model. The target parameterized model of the target three-dimensional object not only has appearance precision close to that of a non-parameterized model, but also has driving parameters capable of being used for driving, automatic conversion from the high-precision non-parameterized model obtained through scanning to the parameterized model is achieved, and the accuracy of the target parameterized model is improved. And the generation efficiency and precision of the high-precision parameterized model are improved.

Description

technical field [0001] The present application relates to the field of data processing, in particular to a method for determining an object model and related devices. Background technique [0002] Scanning a three-dimensional object based on a laser and a large-scale camera array can obtain a high-precision three-dimensional model, which can realistically represent the shape and texture details of the object. However, the scanned 3D model does not have driving parameters, that is, the motion control of the 3D model cannot be performed through processing logic, and it is a non-parametric model. This makes it difficult to apply such non-parametric models to various product scenarios (such as game interaction scenarios, film and television content scenarios). [0003] In related technologies, for the non-parametric model obtained by the aforementioned scanning, after manual processing such as model adjustment, binding, skinning, and material assignment by artists and model des...

AI Technical Summary

Problems solved by technology

[0004] Converting a non-parametric model into a parametric model by manual means is not only time-consuming and labor-intensive, but also relies heavily on human experience, resulting in uncontrollable accuracy of the converted parametric model

Images