Complex object relighting via split-then-composition by semantics and materials
- PDF / 3,405,636 Bytes
- 13 Pages / 439.642 x 666.49 pts Page_size
- 88 Downloads / 192 Views
Complex object relighting via split-then-composition by semantics and materials Xin Jin1,2 · Ning Ning1 · Rui Han1 · Xiaodong Li1 · Xiaokun Zhang1 Received: 29 May 2019 / Revised: 11 May 2020 / Accepted: 15 May 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Complex object illumination transfer is a special challenge in computer vision. In our paper, we put forward a method for complex object illumination transfer. Firstly, the input object image was divided into object components by semantic analysis, to find the reference object images consistent with the object component material in the physical world by material analysis. Material has a great influence on the illumination transfer of object image, so the use of material analysis can greatly reduce the influence of material on the illumination transfer in the later stage. Next, a block matching algorithm was used to deform each reference object image and made it match with each component shape of the input object image. Then, each component of the input object image and each warped reference object image were illuminated by local and global transfer model. Finally, semantic analysis was used to synthesize the re-illumination components of the input object image to obtain the re-illumination input object image. The experimental results prove that the method could make a good effect on the illumination transfer. Our main contribution is the use of semantic and material analysis to split complex objects into simple objects, and skillfully combine semantic and material parsing and composition, block matching algorithm, local and global light migration model to achieve the relighting of complex objects. Keywords Complex object relighting · Illumination transfer · Semantic parsing and composition · Material parsing and composition · Patch match warping · Local and global transfer
1 Introduction To generate images that are indistinguishable from real photographs, traditional graphics techniques require high-precision modelling of the three-dimensional geometry and
Xiaodong Li
[email protected] 1
Beijing Electronic Science and Technology Institute, Beijing, 100070, China
2
State Key Laboratory of Cryptology, P.O. Box 5159, Beijing, 100878, China
Multimedia Tools and Applications
the optical properties of objects’ surface media. However, the existing image-based modelling technology cannot yet meet the requirements of the above-mentioned effects on the accuracy of the three-dimensional model. The concept of image-based virtual illumination generation was born, which can generate realistic illumination effects using less-scale image data. It mainly includes two aspects: one is the generation of illumination effects, mainly to directly change the illumination of the target in the image; the other is the fusion of virtual and real illumination, estimating the lighting conditions of the scene from the image. According to the perspective of the image scene and the lighting conditions, the 3D model is drawn and integrated into th
Data Loading...
