Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion Priors
This addresses the need for large-scale, realistic 3D tree datasets for simulation applications in fields like computer graphics and urban planning, representing a novel domain-specific advancement.
The paper tackles the problem of generating 3D simulation-ready tree models from single images by introducing Tree D-fusion, which produces 600,000 environmentally aware tree models using diffusion priors and genus labels from street view images.
We introduce Tree D-fusion, featuring the first collection of 600,000 environmentally aware, 3D simulation-ready tree models generated through Diffusion priors. Each reconstructed 3D tree model corresponds to an image from Google's Auto Arborist Dataset, comprising street view images and associated genus labels of trees across North America. Our method distills the scores of two tree-adapted diffusion models by utilizing text prompts to specify a tree genus, thus facilitating shape reconstruction. This process involves reconstructing a 3D tree envelope filled with point markers, which are subsequently utilized to estimate the tree's branching structure using the space colonization algorithm conditioned on a specified genus.