Single Viewpoint Image-Driven Simplification

Image-driven simplification has been proposed as a simplification method which generates models with high fidelity and intrinsically factors in the error from mesh appearance properties. However, this approach is very time consuming since it requires multiple render and image captures for each simplification operation. By formulating a new error metric, we devise an image-driven algorithm which requires only one image capture. The proposed single viewpoint simplification runs at least 25 times faster than the previous approach with better quality overall.