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

Portuguese

A geração de peças 3D controlável é essencial para a criação de ativos digitais, mas os métodos existentes carecem da flexibilidade para acomodar fluxos de trabalho de usuários diversos que exigem níveis variáveis de controle. Neste artigo, apresentamos o FlexPart, um framework de geração de peças de imagem unificado para 3D que suporta condições geométricas de granularidade variável dentro de um único modelo. Ao integrar de forma suave entradas heterogêneas, desde pontos escassos a caixas e máscaras densas, através de modulação adaptativa por portas, o FlexPart desbloqueia uma poderosa sinergia entre modos. Também propomos um mecanismo de orientação geométrica assimétrica que aproveita fortes prioridades espaciais para alinhamentos entre granularidades representativas, melhorando a consistência

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