Bas-relief modelling from enriched detail and geometry with deep normal transfer

Self Cite

As the generation of realistic bas-relief models from 2D images suffers from insufficient 3D depth information and severe under-constraint, in this article, we propose a new framework for bas-relief modeling based on 2D decorative images, which adopts conditional generative adversarial network to infer the normal information of the decorative bas-reliefs from the greyscale information extracted from the images. For the variety of models, we extract the internal structure information through the saliency detection method based on scene perception, and use the transfer process based on the optimized texture synthesis algorithm to complete the normal editing from the source normal map to the new one, which can diversify and control the structure and detailed information of existed normal map. Finally, we adopt a bas-relief reconstruction approach based on domain transfer recursive filter and surface from gradient to recover 2.5D information from predicted and transferred normal maps. Experiments on various model examples demonstrate the efficiency and diversity of the proposed method in reconstructing bas-relief models from a single decorative image.

“…The normal images and the structure layer can be subtracted to get the detail layer. The structure layer obtained by domain transfer recursive filter 29 smoothing can be defined as:…”

Section: Bas-relief Modelingmentioning

confidence: 99%

“…The normal images and the structure layer can be subtracted to get the detail layer. The structure layer obtained by domain transfer recursive filter 29 smoothing can be defined as:

J\left(i+1\right)=\left(1-{\alpha}^d\right)N\left(i+1\right)+{\alpha}^dJ(i),

where

i

and

i+1

respectively represent the two adjacent points in the normal map

N

d

is the distance between the two samples, denoted as

1+\frac{\sigma_s}{\sigma_r}\mid I\left(i+1\right)-I(i)\mid

.…”

Section: Algorithmmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Variety decorative bas‐relief generation based on normal prediction and transfer

Shang

Wang

2022

Self Cite

“…This method takes the model height field as the input, extracts the detail features of different scales through convolution network, and finally generates high-quality relief model. Wang et al 8 proposed a modeling method of relief based on visual attention mechanism and transfer learning, which uses semantic neural network to learn texture and structure representation, and generates new texture images on the basis of preserving the richness of relief details.…”

Section: Relief Generationmentioning

confidence: 99%

“…The normalized values and the goodness function are calculated by Equations ( 7) and ( 8), respectively. (8). Similarly, we adopt the least squares optimization to find the parameters of the fitting function.…”

Section: F I G U R E 5 Layouts With Different Separation Distancesmentioning

confidence: 99%

Bas‐relief layout arrangement via automatic method optimization

Mao

Zhang

et al. 2021

Self Cite

It is significant to achieve automatic arrangement for bas-relief layout which can be noticeably more efficient than the time-consuming manual process. In fact, nearly none work has been reported in terms of bas-relief layout arrangement. In this paper, we propose a novel approach to tackle this problem. Specifically, we first identify the evaluation indicators to account for different aesthetic factors, and model the goodness of each indicator. We then cast the bas-relief layout as a combinatorial optimization problem based on those evaluation indicators and a geometric mean model. The contribution of this paper is to propose an objective function for bas-relief layout and apply simulated annealing algorithm for optimization. Experiments show that our method is effective, in terms of layout arrangement for bas-relief generation. In addition, this method can synthesize a few models arrangement and investigate which evaluation indicators will affect the aesthetic perception of the bas-relief.

Detecting color boundaries on 3D surfaces by applying edge‐detection image filters on a quad‐remeshing

Huang

2022

Edge detection is a common image-processing technique that has numerous applications. In this article, we propose an algorithm for detecting edges based on the color of a mesh surface. We name the edges the color boundaries. Our approach is based on the data structure of a quad mesh, which makes the data structure of 3D meshes resemble the data structure of images. As a result, image-processing methods can be applied on the 3D meshes. In this article, six classical edge detection filters are implemented on the 3D meshes. The experimental results demonstrate that our method can identify areas of high color gradient on 3D meshes. A comparison with two other methods for detecting color boundaries on 3D meshes reveals that our method is more effective at detecting boundaries. Lastly, we propose two novel applications that utilize the information of color boundaries on a 3D mesh surface.