Geometry in Style: 3D Stylization via Surface Normal Deformation
This addresses the challenge of balancing shape preservation and expressiveness in 3D stylization for graphics and animation applications, representing an incremental improvement over existing techniques.
The paper tackles the problem of identity-preserving 3D mesh stylization by introducing a method that uses target normal vectors and a differentiable ARAP layer to achieve expressive deformations while preserving shape identity, resulting in detailed stylizations without artifacts.
We present Geometry in Style, a new method for identity-preserving mesh stylization. Existing techniques either adhere to the original shape through overly restrictive deformations such as bump maps or significantly modify the input shape using expressive deformations that may introduce artifacts or alter the identity of the source shape. In contrast, we represent a deformation of a triangle mesh as a target normal vector for each vertex neighborhood. The deformations we recover from target normals are expressive enough to enable detailed stylizations yet restrictive enough to preserve the shape's identity. We achieve such deformations using our novel differentiable As-Rigid-As-Possible (dARAP) layer, a neural-network-ready adaptation of the classical ARAP algorithm which we use to solve for per-vertex rotations and deformed vertices. As a differentiable layer, dARAP is paired with a visual loss from a text-to-image model to drive deformations toward style prompts, altogether giving us Geometry in Style. Our project page is at https://threedle.github.io/geometry-in-style.