深度几何矩促进文本到3D生成中的形状一致性
Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation
AI总结：
MT3D利用高保真3D对象和深度几何矩，克服视角偏差，确保文本到3D生成中的形状一致性，提高3D表示质量。
摘要：
为解决3D资产相关的数据稀缺问题，诸如分数蒸馏采样（SDS）之类的2D提升技术已成为文本到3D生成流程中广泛采用的做法。然而，这些技术中使用的扩散模型容易产生视角偏差，从而导致几何不一致性，例如Janus问题。为应对这一问题，我们引入了MT3D，一种文本到3D生成模型，它利用高保真3D对象来克服视角偏差，并明确地将几何理解注入生成流程。首先，我们采用从高质量3D模型导出的深度图作为控制信号，以确保生成的2D图像保留基本形状和结构，从而减少固有的视角偏差。接下来，我们利用深度几何矩来明确确保3D表示的几何一致性。通过整合来自3D资产的几何细节，MT3D能够创建多样且几何一致的对象，从而提高我们3D表示的质量和可用性。项目页面和代码：https://moment-3d.github.io/
英文摘要：
To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice in text-to-3D generation pipelines. However, the diffusion models used in these techniques are prone to viewpoint bias and thus lead to geometric inconsistencies such as the Janus problem. To counter this, we introduce MT3D, a text-to-3D generative model that leverages a high-fidelity 3D object to overcome viewpoint bias and explicitly infuse geometric understanding into the generation pipeline. Firstly, we employ depth maps derived from a high-quality 3D model as control signals to guarantee that the generated 2D images preserve the fundamental shape and structure, thereby reducing the inherent viewpoint bias. Next, we utilize deep geometric moments to ensure geometric consistency in the 3D representation explicitly. By incorporating geometric details from a 3D asset, MT3D enables the creation of diverse and geometrically consistent objects, thereby improving the quality and usability of our 3D representations. Project page and code: https://moment-3d.github.io/
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。
