Editable Parametric Dense Foliage from 3D Capture


We present an algorithm to compute parametric models of dense foliage.

October 22, 2017
International Conference on Computer Vision (ICCV) 2017



Gaurav Chaurasia (Disney Research)

Paul Beardsley (Disney Research)

Editable Parametric Dense Foliage from 3D Capture


The guiding principles of our work are automatic reconstruction and compact artist friendly representation. We use Bézier patches to model leaf surface, which we compute from images and point clouds of dense foliage. We present an algorithm to segment individual leaves from colour and depth data. We then reconstruct the Bézier representation from segmented leaf points clouds using non-linear optimisation. Unlike previous work, we do not require laboratory scanned exemplars or user intervention. We also demonstrate intuitive manipulators to edit the reconstructed parametric models. We believe our work is a step towards making captured data more accessible to artists for foliage modelling.

Additional Content

Copyright Notice