Botanical tree reconstruction from a single image via 3D GAN-based skeletonization

Background 3D botanical tree reconstruction from a single image plays a vital role in the field of computer graphics. However, accurately capturing the intricate branching patterns and detailed morphologies of trees remains a challenge. Methods In this study, we proposed a novel approach for single-image tree reconstruction using a conditional generative adversarial network to infer the 3D skeleton of a tree in the form of a 2D skeleton depth map. Based on the 2D skeleton depth map, a corresponding branching structure (3D skeleton) that inherits the tree shape in the input image and leaves can be generated using a procedural modeling technique. Result Experimental results show that the proposed method accurately reconstructs diverse tree structures across species. Both quantitative and qualitative evaluations demonstrate improved skeleton completeness, branching accuracy, and visual realism over baseline methods, while requiring no user input. Conclusions Our proposed approach for generating lifelike 3D tree models from a single image with no user input shows its proficiency in achieving efficient and reliable reconstruction. These results showcase the capability of the proposed model to recreate complex tree architectures while capturing their visual authenticity.