Semantic-driven 3D shape generation aims to generate 3D objects conditioned on text. Previous works face problems with single-category generation, low-frequency 3D details, and requiring a large number of paired datasets for training. To tackle these challenges, we propose a multi-category conditional diffusion model. Specifically, 1) to alleviate the problem of lack of large-scale paired data, we bridge the text, 2D image and 3D shape based on the pre-trained CLIP model, and 2) to obtain the multi-category 3D shape feature, we apply the conditional flow model to generate 3D shape vector conditioned on CLIP embedding. 3) to generate multi-category 3D shape, we employ the hidden-layer diffusion model conditioned on the multi-category shape vector, which greatly reduces the training time and memory consumption.
翻译:以语义驱动的 3D 形状生成旨在生成以文本为条件的 3D 对象。 以往的工作面临单类生成、 低频 3D 细节和需要大量配对数据集的培训问题。 为了应对这些挑战, 我们提议了一个多类有条件的扩展模式。 具体地说, 1) 缓解缺少大型配对数据的问题, 我们根据经过预先培训的 CLIP 模型将文本、 2D 图像和 3D 形状连接起来, 2) 获取多类 3D 形状特征, 我们使用有条件的流程模式生成以 CLIP 嵌入为条件的 3D 形状矢量 。 3) 生成多类 3D 形状, 我们使用以多类形状矢量为条件的隐藏层扩散模式, 这极大地减少了培训时间和记忆消耗 。