TL;DR通过利用先前训练好的生成模型,通过领域自适应的方式,基于有限数量的训练数据从而实现了少样本 3D 形状生成,该方法能够在保持多样性的同时避免过度拟合,并通过多种度量评估了生成的质量和多样性。
Abstract
Realistic and diverse 3d shape generation is helpful for a wide variety of
applications such as virtual reality, gaming, and animation. Modern generative
models, such as GANs and diffusion models, learn from large-scale datasets and
generate new samples following similar data distribut
This paper explores the use of pre-trained models and synthetic renderings to generate 3D shapes from sketches without the need for paired datasets, demonstrating the effectiveness of the approach for generating multiple 3D shapes per input sketch regardless of their level of abstraction.