cs.CVNov 16, 2026

VA-Assembly: View-Aligned Score Guidance for Training-Free 3D Part Assembly

Authors: Yeon-Jae Kim, Sangwon Kang, Byung-Kwon Min

Organizations: School of Mechanical Engineering, Yonsei University, Seoul, Republic of Korea.

Abstract

Image-to-3D foundation models have improved 3D reconstruction, but typically produce monolithic representations without explicit part-level structure. Part-aware generation and learning-based assembly methods often require part-level supervision, category-specific priors, or paired part-layout training data. We instead consider a practical but underexplored setting in which independently prepared or generated 3D parts have no predefined inter-part relationships, shared coordinate frames, or consistent scales, and must be assembled into a reference-consistent object from a single image. We present VA-Assembly, a training-free framework for 3D part assembly through part-level transformation estimation using view-aligned diffusion guidance. Given a reference image and fixed 3D part geometries, VA-Assembly optimizes each part's translation, rotation, and scale. We condition a frozen view-conditioned diffusion model on same-view renderings of a reference-derived monolithic 3D representation, producing score gradients geometrically aligned with the part configuration. This guidance provides multi-view structural cues under large initial misalignment. By repurposing pretrained visual-structural priors as transformation-level supervision, VA-Assembly requires no annotated part layouts, predefined part taxonomies, category-specific assembly training, or bounding-box-based layout initialization. Experiments compare VA-Assembly with geometric registration and compositional layout baselines using each baseline's supported transformation components, showing improved part-wise transformation estimation. Ablation studies show that view-aligned conditioning, rather than diffusion guidance alone, is critical for reliable transformation gradients. Updating only part transformations preserves explicit component separability and supports component-level editing, replacement, and reconfiguration.

Figures & tables

Explore similar work

CardsList
  1. PART: Learning 3D Part Assembly and Retrieval with Transformers

    Sep 17, 2026Ruchao Bao, Wenzheng Wu, Chucheng Xiang +53D Reconstruction

  2. CRAG: Can 3D Generative Models Help 3D Assembly?

    Feb 26, 2026Zeyu Jiang, Sihang Li, Siqi Tan +83D Shape GenerationPart-Level 3D Generation

  3. LLM2R: From Large Language Models to 3D Reassemblers

    Oct 13, 2026Zhouhan Zhong, Qiuhong Shen, Xingyi Yang +23D Reconstruction