Newest papers

A Unified Framework for Image-to-3D Part Generation via Variable Granularity

Qiwen Gu, Xin Zhou, Xiwu Chen, Zhongyang Zhu, Zhuo Zhang, Junqiao Zhao · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31671 · cited by 0 works (OpenAlex) · open-access PDF

Hindi

नियंत्रित 3 डी पार्ट्स जनरेटिंग डिजिटल संपत्ति बनाने के लिए महत्वपूर्ण है, फिर भी मौजूदा तरीकों को विभिन्न उपयोगकर्ता कार्य प्रवाहों को समायोजित करने के लिए लचीलापन की कमी है, जिसमें विभिन्न स्तरों के नियंत्रण की आवश्यकता होती है। इस लेख में, हम FlexPart, एक एकीकृत छवि-to-3D पार्ट्स जनरेटिंग फ्रेमचर को पेश करते हैं जो एक ही मॉडल के भीतर परिवर्तनीय-ग्रेनेलता भूमेट्रिक स्थितियों का समर्थन करता है। विभिन्न प्रकार के उपयोगकर्ता कार्य प्रवाहों को आसानी से एकीकृत करके, छोटे बिंदुओं से घने सीमा बॉक्सों और मास्क तक, गेट एडाप्टिव मॉड्यूलेशन के माध्यम से, FlexPart एक शक्तिशाली क्रॉस-मोड जनरेटिंग फ्रे

Machine translation (Meta M2M100); the English original follows.

Abstract

Controllable 3D part generation is pivotal for digital asset creation, yet existing methods lack the flexibility to accommodate diverse user workflows requiring varying levels of control. In this paper, we introduce FlexPart, a unified image-to-3D part generation framework that supports variable-granularity geometric conditions within a single model. By seamlessly integrating heterogeneous inputs, ranging from sparse points to dense bounding boxes and masks, via gated adaptive modulation, FlexPart unlocks a powerful cross-modal synergy. We also propose an asymmetric geometric guidance mechanism that leverages strong spatial priors to align representations across granularities, improving geometric consistency and facilitating inter-task synergy. Under mask conditioning on PartVerseXL, FlexPart reduces Part CD by 16.6% relative to TripoSG + SAM3D and by 10.5% relative to OmniPart, while maintaining competitive whole-mesh quality. The code can be found at https://github.com/Gucci233/FlexPart

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Granularity, Consistency (knowledge bases), Ranging, Workflow, Bounding overwatch

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31671, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange