Object surface reflection attribute extraction method, device and equipment and storage medium

Abstract

The invention discloses an object surface reflection attribute extraction method, and the method proposes a Berlin noise-based synthetic data set, generates textures with low-frequency and high-frequency feature distribution, supports the generation of a data set sample, solves a problem of insufficient training data, and carries out the synthesis of sample data based on Berlin noise. A data set similar to a real sample can be expressed, and the generalization of the network is further improved; besides, the invention also provides an auto-encoder network structure based on VGG-19 and UNet network models, the network performs histogram matching on a feature map, feature extraction is performed through a hole convolution strategy, and the network is trained in combination with weak supervision and rendering technologies so as to obtain an auto-encoder network structure based on VGG-19 and UNet network models. The precision and the quality of the extracted object surface reflection attribute are effectively improved. The invention further provides an object surface reflection attribute extraction device and equipment and a readable storage medium, which have the above beneficial effects.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a method, device, equipment and a readable storage medium for extracting reflective properties of object surfaces. Background technique [0002] The 3D modeling of real objects includes 3D geometric modeling and surface reflection attribute modeling. 3D geometric modeling can use 3D scanners for data collection, or artists can use Maya, 3DMax and other professional modeling software to make models. However, the process of modeling the surface reflection properties of objects is very complicated, and the surface reflection properties of different samples are not the same. There are many difficulties in the modeling of surface reflection properties. Factors such as blur will affect the quality and accuracy of the generated results. How to stably and reliably generate surface reflection properties with high quality and without loss of image details has always...

AI Technical Summary

Problems solved by technology

[0006] However, when the convolutional neural network is used to process the input image and generate a diffuse reflection map, there will be problems such as uneven brightness and darkness, excessive illumination, excessive darkness, or loss of feature distribution information. For a local high-intensity point light source, it is impossible to Accurate analysis of its highlight structure will mistake the highlight for the color of the texture itself. At the same time, when the output size increases, the optimization and synthesis process will gradually become unstable during iterations, and texture regularity will be lost.

Images