Smart deformation and warping tools play an important part in modern day geometric modeling systems. They allow existing content to be stretched or scaled while preserving visually salient information. To date, these techniques have primarily focused on preserving local shape details, not taking into account important global structures such as symmetry and line features.

In this project we developed a novel framework that can be used to preserve the global structure in images and vector art. Such structures include symmetries and the spatial relations in shapes and line features in an image. Central to our method is a new formulation of preserving structure as an optimization problem. We use novel optimization strategies to achieve the interactive performance required by modern day modeling applications. We demonstrate the effectiveness of our framework by performing structure preservation deformation of images and complex vector art at interactive rates.

Peter1a_v2_002

1a

Peter1d_v2_000

1d

Peter1g_v2_000

1g

Peter1b_v2

1b

Peter1e_v2_000

1e

Peter1c_v2_000

1c

Peter1f_v2_000

1f

Figure 1: Resizing an image in which the line features and the people in the middle are prominent features. Our method tries to preserve these line features and shape of the people together which exhibits much less visual distortion compared with existing techniques. (a) Upper: The input image. Bottom: the line features and the deformation map. (b) Homogeneous scaling. (c) Our method. (d) Content-driven Retargeting. (e) Seam Carving. (f) Indirect Seam Carving with the people and the lane being marked. (g) Optimized Scale-and-Stretch.

peter2a_v2

2a

peter2c_v2_000

2c

peter2b_v2_000

2b

peter2d_v2

2d

Figure 2: Comparison on resizing the Chinese art shown in (a):  (b) Ours. (c) Seam Carving. (d) Optimized Scale-and-Stretch.