Seg3DParts is presented, a segmentation-grounded framework for controllable part-level 3D generation from a single image, and structured cross-part interaction that allows components to exchange global context throughout the generative process is introduced.
Abstract
Part-level 3D assets are essential for editing, reassembly, and interaction, yet recovering such structure from a single image remains challenging due to occlusion, ambiguous boundaries, and the need for coherent multi-part reasoning. Existing approaches struggle to achieve both controllable part-level generation and coherent multi-part structure, as part identity and spatial allocation are typically inferred implicitly. We present Seg3DParts, a segmentation-grounded framework for controllable part-level 3D generation from a single image. By treating segmentation as an explicit grounding signal, our method defines part identity during generation, enabling each component to be anchored to a corresponding image region. To ensure coherent assemblies, we introduce structured cross-part interaction that allows components to exchange global context throughout the generative process. As a result, Seg3DParts directly generates well-aligned part meshes in a shared canonical space without post-hoc alignment, supporting flexible and controllable decomposition. We further introduce PartObjectNet, a large-scale dataset with over 200K objects and 1M annotated parts. Experiments demonstrate that Seg3DParts achieves superior geometry quality, cross-part coherence, and part-level controllability over existing methods.
Part-level control is essential for modern 3D asset creation, where objects are frequently edited, reused, animated, or fabricated through their individual components. In many such workflows, users need only several specific components rather than a complete object decomposition. However, existing 3D generation methods...
Jia-Hao Chang, Dong Du, Wan-Hu Sun et al.· 0 citations
SCULPT iteratively applies a joint split predictor to generate one extracted part together with the remaining object, and demonstrates state-of-the-art geometry on PartObjaverse while preserving strong complete-object reconstruction after part assembly.
Sikuang Li, Chen Yang, Jie-Min Fang et al.· 0 citations
Part segmentation is a fundamental problem in computer graphics and 3D vision. Recent works have expanded 3D part segmentation beyond fixed taxonomies, but existing approaches typically only address a specific setting, such as text-guided part segmentation or point-based interaction. In this work, we argue that these s...
Zhe Zhu, Yi-Heng Zhang, Peng Li et al.· 1 citation
3DCoder, a framework that converts a single image into a structured and executable 3D representation suitable for editing and physics-based simulation, and a dataset that jointly annotates part geometry, kinematic hierarchies, articulation parameters, materials, and non-tree relations across articulated objects, proced...
Experiments demonstrate that the MultiCube method can generate high-quality compositional 3D objects with precise part-level control, including those with unique layouts difficult to achieve with text or image prompting alone.
Ava Pun, Kang-Le Deng, Yi-Heng Zhu et al.· 0 citations
Generative models have rapidly pushed content creation be-yond 2D imagery toward dynamic 3D and 4D scene synthesis. Yet pro-ducing realistic and temporally stable 4D content from a single image is still difficult because one view provides limited structural cues and weak motion evidence. We introduce MATE4D, a framewor...
Xiao-Tian Chen, Dong-Fu Yin· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.