Image-based plant modeling
Long Quan, Ping Tan, Gang Zeng et al. · ACM Transactions on Graphics · 2006
In this paper, we propose a semi-automatic technique for modeling plants directly from images. Our image-based approach has the distinct advantage that the resulting model inherits the realistic shape and complexity of a real plant. We designed our modeling system to be interactive, automating the process of shape recovery while relying on the user to provide simple hints on segmentation. Segmentation is performed in both image and 3D spaces, allowing the user to easily visualize its effect immediately. Using the segmented image and 3D data, the geometry of each leaf is then automatically recovered from the multiple views by fitting a deformable leaf model. Our system also allows the user to easily reconstruct branches in a similar manner. We show realistic reconstructions of a variety of plants, and demonstrate examples of plant editing.
Cited by 279 works. doi:10.1145/1141911.1141929
Authors
References
- Multiple View Geometry in Computer Vision
- Normalized cuts and image segmentation
- A method for registration of 3-D shapes
- Fast approximate energy minimization via graph cuts
- Lazy snapping
- The Geometry of Multiple Images
- Multiple View Geometry in Computer Vision.
- Visual models of plants interacting with their environment
- Plant models faithful to botanical structure and development
- The Geometry of Multiple Images: The Laws that Govern the Formation of Multiple Images of a Scene and Some of Their Applications