SCULPT: Subtractive Composition for 3D Part Generation

• URL: http://arxiv.org/abs/2608.13541v1
• Date: Thu, 13 Aug 2026 17:55:04 GMT
• Title: SCULPT: Subtractive Composition for 3D Part Generation
• Abstract summary: Part-aware 3D generation aims to create digital assets that are coherent as complete objects.<n>We propose SCULPT, a framework that addresses these challenges through subtractive composition.
• Score: 48.947695076233835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Part-aware 3D generation aims to create digital assets that are coherent as complete objects while exposing structural parts for editing, material assignment, animation, and reuse. Existing methods impose this structure outside the native generation loop: segmentation-based methods partition an already generated shape, while additive methods synthesize parts from predefined layouts, boxes, or tokens and then reconcile them into a whole. The former preserves the generated geometry but fixes the object before part boundaries are determined; the latter exposes part cardinality but often leaves shared boundaries vulnerable to gaps, interpenetrations, and material discontinuities. In this paper, we propose SCULPT, a framework that addresses these challenges through subtractive composition. Given a complete object represented in a structured 3D latent space, SCULPT iteratively applies a joint split predictor to generate one extracted part together with the remaining object. The predictor performs a coupled denoising process conditioned on both the image and the current 3D state, so the extracted part and updated remainder are generated together rather than reconciled after generation. The joint split predictor processes both outputs on the union of their native sparse 3D supports, allowing neighboring supports to overlap rather than imposing a disjoint voxel partition. The rollout ends when the remainder support becomes empty or reaches a fixed safety cap, allowing the number of generated parts to adapt to each object within that bound. Extensive experiments demonstrate state-of-the-art geometry on PartObjaverse while preserving strong complete-object reconstruction after part assembly. Results on four dataset images, one text-to-image-generated input, and one real-world photograph further show fine-grained textured part decomposition beyond the benchmark.

Related papers

• SAM3D-Part: Interactive Part Selection and Generation from 3D Objects [20.379932054770588]
  We present SAM3D-Part, a prompt-driven framework for selective part generation from input 3D object meshes.<n>Experiments and ablations demonstrate that SAM3D-Part can significantly improve source alignment, reduce conditioning cost, and enable consistent selective part generation.
  arXiv  Detail & Related papers  (2026-09-14T14:26:34Z)
• PartMat: Material-Aware 3D Part Decomposition with a Single Global Latent [7.354114153015086]
  Part-level 3D generation has attracted increasing attention for producing structured and editable 3D assets.<n>Existing methods typically decompose objects according to functional semantics rather than the editable material boundaries.<n>We present PartMat, an efficient material-aware 3D part decomposition pipeline that represents multi-part geometry with a single global latent.
  arXiv  Detail & Related papers  (2026-08-03T07:32:10Z)
• Beyond Spatial Compression: Interface-Centric Generative States for Open-World 3D Structure [55.17771962316751]
  Current 3D tokenizers treat representation as spatial compression, but leave component ownership and attachment validity implicit.<n>We formulate an alternative view, interface-centric generative states, in which tokenization constructs an operational state rather than a passive compressed code.<n>We instantiate this formulation with Component-Conditioned Canonical Local Tokens (C2LT-3D), factorizing representation into canonical local geometry, partition-conditioned context, and relational seam variables.
  arXiv  Detail & Related papers  (2026-05-11T12:09:28Z)
• AutoPartGen: Autogressive 3D Part Generation and Discovery [66.14255946353475]
  We introduce AutoPartGen, a model that generates objects composed of 3D parts in an autoregressive manner.<n>This model can take as input an image of an object, 2D masks of the object's parts, or an existing 3D object, and generate a corresponding compositional 3D reconstruction.<n>We evaluate both the overall 3D generation capabilities and the part-level generation quality of AutoPartGen, demonstrating that it achieves state-of-the-art performance in 3D part generation.
  arXiv  Detail & Related papers  (2025-07-17T17:59:47Z)
• Efficient Part-level 3D Object Generation via Dual Volume Packing [51.712083185732894]
  We propose a new end-to-end framework for part-level 3D object generation.<n>Our method generates high-quality 3D objects with an arbitrary number of complete and semantically meaningful parts.
  arXiv  Detail & Related papers  (2025-06-11T17:55:03Z)
• PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers [29.52313100024294]
  We introduce PartCrafter, the first structured 3D generative model that jointly synthesizes multiple semantically meaningful and geometrically distinct 3D meshes from a single RGB image.<n>PartCrafter simultaneously denoises multiple 3D parts, enabling end-to-end part-aware generation of both individual objects and complex multi-object scenes.<n> Experiments show that PartCrafter outperforms existing approaches in generating decomposable 3D meshes.
  arXiv  Detail & Related papers  (2025-06-05T20:30:28Z)
• PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models [63.1432721793683]
  We introduce PartGen, a novel approach that generates 3D objects composed of meaningful parts starting from text, an image, or an unstructured 3D object.<n>We evaluate our method on generated and real 3D assets and show that it outperforms segmentation and part-extraction baselines by a large margin.
  arXiv  Detail & Related papers  (2024-12-24T18:59:43Z)
• Part123: Part-aware 3D Reconstruction from a Single-view Image [54.589723979757515]
  Part123 is a novel framework for part-aware 3D reconstruction from a single-view image. We introduce contrastive learning into a neural rendering framework to learn a part-aware feature space. A clustering-based algorithm is also developed to automatically derive 3D part segmentation results from the reconstructed models.
  arXiv  Detail & Related papers  (2024-05-27T07:10:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.