Papers for

digital asset creators

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

FlexPart enables flexible image-based 3D part creation with varied input detail

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

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

Thu 22 OctComputer Vision and Pattern Recognition

The gist

Making 3D parts from images usually requires users to provide detailed instructions, which can be limiting. The authors propose FlexPart, a system that lets users control 3D part creation through different types of guidance, from simple points to detailed masks, all handled by one model. This approach helps produce more accurate and consistent 3D parts, improving on previous methods. The system combines these different inputs smartly and maintains high-quality full shapes.

Open → 2610.31671v1