Turbo3D:超快文本到3D生成
Turbo3D: Ultra-fast Text-to-3D Generation
AI总结:
提出 Turbo3D 文本到3D系统,通过 Dual-Teacher 蒸馏的4步4视图潜空间扩散生成器与潜空间 Gaussian 重建器,在一秒内生成高质量3D资产。
摘要:
我们提出 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 Gaussian splatting 资产。Turbo3D 采用快速的4步、4视图扩散生成器和高效的前馈 Gaussian 重建器,二者均在潜空间中运行。该4步、4视图生成器是通过新颖的 Dual-Teacher 方法蒸馏得到的学生模型,该方法鼓励学生从多视图教师学习视图一致性,并从单视图教师学习照片级真实感。通过将 Gaussian 重建器的输入从像素空间转移到潜空间,我们消除了额外的图像解码时间,并将 transformer 序列长度减半以实现最高效率。与以往基线相比,我们的方法展示出更优的3D生成结果,而运行时间仅为它们的一小部分。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。