Turbo3D：超快速文本到3D生成

Turbo3D: Ultra-fast Text-to-3D Generation

December 5, 2024

作者: Hanzhe Hu, Tianwei Yin, Fujun Luan, Yiwei Hu, Hao Tan, Zexiang Xu, Sai Bi, Shubham Tulsiani, Kai Zhang

cs.AI

摘要

我们介绍了 Turbo3D，这是一个超快的文本到3D系统，能够在不到一秒的时间内生成高质量的高斯飘带资产。Turbo3D采用了一个快速的4步骤、4视图扩散生成器和一个高效的前馈高斯重构器，两者都在潜在空间中运行。4步骤、4视图生成器是通过一种新颖的双教师方法提炼出的学生模型，该方法鼓励学生从多视图教师那里学习视图一致性，从单视图教师那里学习照片逼真性。通过将高斯重构器的输入从像素空间转移到潜在空间，我们消除了额外的图像解码时间，并将变压器序列长度减半，以实现最大效率。我们的方法在运行时间的一小部分内展示了优越的3D生成结果，相比之前的基线方法而言。

English

We present Turbo3D, an ultra-fast text-to-3D system capable of generating high-quality Gaussian splatting assets in under one second. Turbo3D employs a rapid 4-step, 4-view diffusion generator and an efficient feed-forward Gaussian reconstructor, both operating in latent space. The 4-step, 4-view generator is a student model distilled through a novel Dual-Teacher approach, which encourages the student to learn view consistency from a multi-view teacher and photo-realism from a single-view teacher. By shifting the Gaussian reconstructor's inputs from pixel space to latent space, we eliminate the extra image decoding time and halve the transformer sequence length for maximum efficiency. Our method demonstrates superior 3D generation results compared to previous baselines, while operating in a fraction of their runtime.