Atlas3D：物理約束的自支撐文本轉3D，用於模擬和製造

Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication

May 28, 2024

作者: Yunuo Chen, Tianyi Xie, Zeshun Zong, Xuan Li, Feng Gao, Yin Yang, Ying Nian Wu, Chenfanfu Jiang

cs.AI

摘要

現有基於擴散的文本轉3D生成方法主要專注於產生外觀逼真的形狀和外貌，常常忽略下游任務所需的物理限制。生成的模型在放置在基於物理的模擬或3D列印中時，經常無法保持平衡。這種平衡對於滿足互動遊戲、具身體感知的人工智能和機器人技術中用戶設計意圖至關重要，需要穩定的模型以進行可靠的互動。此外，穩定的模型確保了3D列印的物件，例如家居裝飾用的小雕像，可以獨立站立而無需額外支撐。為填補這一空白，我們引入了Atlas3D，一種自動且易於實施的方法，可增強現有基於得分蒸餾採樣（SDS）的文本轉3D工具。Atlas3D確保生成符合重力、接觸和摩擦物理穩定性法則的自支撐3D模型。我們的方法結合了一種新穎的可微分基於模擬的損失函數和受物理啟發的正則化，可作為現有框架的精煉或後處理模塊。我們通過廣泛的生成任務驗證了Atlas3D的效能，並在模擬和現實環境中驗證了生成的3D模型。

English

Existing diffusion-based text-to-3D generation methods primarily focus on producing visually realistic shapes and appearances, often neglecting the physical constraints necessary for downstream tasks. Generated models frequently fail to maintain balance when placed in physics-based simulations or 3D printed. This balance is crucial for satisfying user design intentions in interactive gaming, embodied AI, and robotics, where stable models are needed for reliable interaction. Additionally, stable models ensure that 3D-printed objects, such as figurines for home decoration, can stand on their own without requiring additional supports. To fill this gap, we introduce Atlas3D, an automatic and easy-to-implement method that enhances existing Score Distillation Sampling (SDS)-based text-to-3D tools. Atlas3D ensures the generation of self-supporting 3D models that adhere to physical laws of stability under gravity, contact, and friction. Our approach combines a novel differentiable simulation-based loss function with physically inspired regularization, serving as either a refinement or a post-processing module for existing frameworks. We verify Atlas3D's efficacy through extensive generation tasks and validate the resulting 3D models in both simulated and real-world environments.