Two-and-a-half-dimensional (2.5-D) cartoon models are popular methods used for simulating three-dimensional (3-D) movements, such as out-of-plane rotation, from two-dimensional (2-D) shapes in different views without 3-D models. However, cartoon objects and characters have several exaggerations that do not correspond to any real 3-D positions (e.g., Mickey Mouse's ears), which implies that existing methods are unsuitable for designing such exaggerations. Hence, we incorporated view-dependent deformation (VDD) techniques, which have been proposed in the field of 3-D character animation, into 2.5-D cartoon models. The exaggerations in an arbitrary viewpoint are automatically obtained by blending the user-specified 2-D shapes of key views. Several examples demonstrated the robustness of our method over previous methods. In addition, we conducted a user study and confirmed that the proposed method is effective for animating classic cartoon characters.