用扩散模型生成高精度3D服装动画，支持多种体型和设计。
DiffusedWrinkles: A Diffusion-Based Model for Data-Driven Garment Animation
- 将3D服装变形转为2D纹理表示，保持布局一致性。
- 可生成依赖姿势、体型和设计的高质量3D服装动画。
- 支持从已有状态延续生成连贯动画，适合虚拟试衣场景。
我们提出一种基于2D图像扩散模型的数据驱动方法，用于生成3D服装动画。与传统基于全连接网络、图神经网络或生成对抗网络的方法不同，该方法能有效处理具有精细褶皱细节的参数化服装，且对服装网格拓扑结构无依赖。核心思想是将3D服装变形表示为相对于参数化模板的2D布局一致纹理，编码三维偏移量。利用大量在不同动作和体型下模拟的服装数据训练新型条件扩散模型，可生成依赖姿态、体型和设计的高质量3D服装变形。由于模型具备生成能力，对于给定目标姿态、体型和设计，可合成多种合理变形。此外，我们还展示了通过已有服装状态进行条件控制，实现时间上连贯的动画序列生成。
原文摘要 · Abstract (English)
We present a data-driven method for learning to generate animations of 3D garments using a 2D image diffusion model. In contrast to existing methods, typically based on fully connected networks, graph neural networks, or generative adversarial networks, which have difficulties to cope with parametric garments with fine wrinkle detail, our approach is able to synthesize high-quality 3D animations for a wide variety of garments and body shapes, while being agnostic to the garment mesh topology. Our key idea is to represent 3D garment deformations as a 2D layout-consistent texture that encodes 3D offsets with respect to a parametric garment template. Using this representation, we encode a large dataset of garments simulated in various motions and shapes and train a novel conditional diffusion model that is able to synthesize high-quality pose-shape-and-design dependent 3D garment deformations. Since our model is generative, we can synthesize various plausible deformations for a given target pose, shape, and design. Additionally, we show that we can further condition our model using an existing garment state, which enables the generation of temporally coherent sequences.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。