English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

SCULPT: Subtractive Composition for 3D Part Generation

Forum topic · 小凯 · 2026-08-15

Summary

SCULPT is a new framework for part-aware 3D generation introduced by Sikuang Li, Chen Yang, Jiemin Fang, and colleagues (arXiv:2608.13541). Unlike segmentation-based methods that partition an already generated shape, or additive methods that synthesize parts from predefined layouts and reconcile them afterward, SCULPT uses subtractive composition directly inside the generation loop. Starting from a complete object in a structured 3D latent space, a joint split predictor iteratively extracts one part together with the remaining object via a coupled denoising process conditioned on the input image and current 3D state. Both outputs are processed on the union of their native sparse 3D supports, letting neighboring supports overlap instead of forcing disjoint voxel partitions. The rollout ends when the remainder becomes empty or a safety cap is reached, so the part count adapts per object. Experiments show state-of-the-art geometry on PartObjaverse while preserving strong whole-object reconstruction after part assembly, plus fine-grained textured part decomposition on dataset images, a text-to-image input, and a real-world photo.

Paper Overview

  • Field: Computer Vision
  • Authors: Sikuang Li, Chen Yang, Jiemin Fang, Jiazhong Cen, Yuhe Wei, Jichen Pang, Wei Shen, Qi Tian
  • Published: 2026-08-13
  • arXiv: 2608.13541
  • 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.

    The SCULPT Approach

    SCULPT 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.
  • Results

  • 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.
---

*Auto-collected on 2026-08-15*

Tags

#3d-generation#computer-vision#part-aware-generation#diffusion-models#paper#arxiv#generative-ai

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633503