Image-based tree modeling
Ping Tan, Gang Zeng, Jingdong Wang et al. · ACM SIGGRAPH Conference Papers (SIGGRAPH) · 2007
In this paper, we propose an approach for generating 3D models of natural-looking trees from images that has the additional benefit of requiring little user intervention. While our approach is primarily image-based, we do not model each leaf directly from images due to the large leaf count, small image footprint, and widespread occlusions. Instead, we populate the tree with leaf replicas from segmented source images to reconstruct the overall tree shape. In addition, we use the shape patterns of visible branches to predict those of obscured branches. We demonstrate our approach on a variety of trees.
Cited by 190 works. doi:10.1145/1275808.1276486
Authors
References
- Mean shift: a robust approach toward feature space analysis
- Texture synthesis by non-parametric sampling
- Visual models of plants interacting with their environment
- Plant models faithful to botanical structure and development
- A quasi-dense approach to surface reconstruction from uncalibrated images
- Synthetic topiary
- Creation and rendering of realistic trees
- Bayesian Reconstruction of 3D Shapes and Scenes From A Single Image
- The use of positional information in the modeling of plants
- Reconstructing 3D tree models from instrumented photographs