SVDTree: Semantic Voxel Diffusion for Single Image Tree Reconstruction

Efficiently representing and reconstructing the 3D geometry of biological trees remains a challenging problem in computer vision and graphics. We propose a novel approach for generating realistic tree models from single-view photographs. We cast the 3D information inference problem to a semantic voxel diffusion process, which converts an input image of a tree to a novel Semantic Voxel Structure (SVS) in 3D space. The SVS encodes the geometric appearance and semantic structural information (e.g., classifying trunks, branches, and leaves), which retains the intricate internal tree features. Tailored to the SVS, we present SVDTree a new hybrid tree modeling approach by combining structure-oriented branch reconstruction and self-organization-based foliage reconstruction. We validate SVDTree by using images from both synthetic and real trees. The comparison results show that our approach can better preserve tree details and achieve more realistic and accurate reconstruction results than previous methods.

1. Introduction

Vegetation is an indispensable part of natural and urban scenes. However, capturing the vegetation is a complex task that is dominated by procedural models [46], [48], [52], [66]. Recently, plant reconstruction methods have seen a significant improvement and have found applications in areas such as plant geometry and topology for vision-assisted plant phenotyping [19], [37], forestry [24] or counting [44].