OmniPart：具備語意解耦與結構凝聚力的部件感知3D生成

摘要

創建具有明確、可編輯部件結構的3D資產對於推進互動應用至關重要，然而大多數生成方法僅能產出單一形狀，限制了其實用性。我們提出了OmniPart，這是一個新穎的部件感知3D物體生成框架，旨在實現組件間的高度語義解耦，同時保持堅固的結構凝聚力。OmniPart獨特地將這一複雜任務解耦為兩個協同階段：(1) 一個自迴歸結構規劃模塊生成可控、可變長度的3D部件邊界框序列，關鍵在於靈活的2D部件掩碼引導，允許直觀控制部件分解，無需直接對應或語義標籤；(2) 一個空間條件化的修正流模型，高效地從預訓練的整體3D生成器改編，在規劃的佈局內同時且一致地合成所有3D部件。我們的方法支持用戶定義的部件粒度、精確定位，並能實現多樣化的下游應用。大量實驗表明，OmniPart達到了最先進的性能，為更可解釋、可編輯和多功能化的3D內容鋪平了道路。

English

The creation of 3D assets with explicit, editable part structures is crucial for advancing interactive applications, yet most generative methods produce only monolithic shapes, limiting their utility. We introduce OmniPart, a novel framework for part-aware 3D object generation designed to achieve high semantic decoupling among components while maintaining robust structural cohesion. OmniPart uniquely decouples this complex task into two synergistic stages: (1) an autoregressive structure planning module generates a controllable, variable-length sequence of 3D part bounding boxes, critically guided by flexible 2D part masks that allow for intuitive control over part decomposition without requiring direct correspondences or semantic labels; and (2) a spatially-conditioned rectified flow model, efficiently adapted from a pre-trained holistic 3D generator, synthesizes all 3D parts simultaneously and consistently within the planned layout. Our approach supports user-defined part granularity, precise localization, and enables diverse downstream applications. Extensive experiments demonstrate that OmniPart achieves state-of-the-art performance, paving the way for more interpretable, editable, and versatile 3D content.

OmniPart：具備語意解耦與結構凝聚力的部件感知3D生成

OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion

摘要

Support