Capture And Reconstruct The Growing Plants

Growing plants is a beautiful phenomenon in nature as plants like flowers open in an intricate and complex manner whereas leaves bend, stretch and twist under various deformations. Leaves or petals are typically thin structures arranged in tight configurations with heavy self-occlusions. Thus, capturing and reconstructing spatially and temporally coherent sequences of growing plants is highly challenging. Early in the process only exterior leaves are visible and thus interior parts will be completely missing in the captured data. Utilizing commercially available 3D scanners, we capture the visible parts of growing plants into a sequence of 3D point clouds. We reconstruct the plant geometry and deformation over time using a template-based dynamic tracking algorithm. To track and model interior leaves hidden in early stages of the blooming process, we employ an adaptively constrained optimization. Our methods allow us to faithfully reconstruct the growing process of different species which we demonstrate in our results. We provide comparisons with state-of-the-art physical simulation-based approaches and evaluate our approach by using photos of captured real plants.