A Pixel-Based Framework for Data-Driven Clothing
This work addresses the challenge of creating more lifelike clothing animations in computer graphics, which is incremental as it builds on existing image-based techniques like CNNs and GANs.
The paper tackles the problem of generating realistic virtual cloth deformations by proposing a framework that recasts 3D cloth deformation as 2D RGB images in pattern space, enabling the use of CNNs to learn deformations driven by animation parameters like joint angles, resulting in a method that does not require accurate unclothed body shapes or robust skinning techniques.
With the aim of creating virtual cloth deformations more similar to real world clothing, we propose a new computational framework that recasts three dimensional cloth deformation as an RGB image in a two dimensional pattern space. Then a three dimensional animation of cloth is equivalent to a sequence of two dimensional RGB images, which in turn are driven/choreographed via animation parameters such as joint angles. This allows us to leverage popular CNNs to learn cloth deformations in image space. The two dimensional cloth pixels are extended into the real world via standard body skinning techniques, after which the RGB values are interpreted as texture offsets and displacement maps. Notably, we illustrate that our approach does not require accurate unclothed body shapes or robust skinning techniques. Additionally, we discuss how standard image based techniques such as image partitioning for higher resolution, GANs for merging partitioned image regions back together, etc., can readily be incorporated into our framework.