Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SARe: Structure-Aware Large-Scale 3D Fragment Reassembly

Hanze Jia, Chunshi Wang, Yuxiao Yang, Zhonghua Jiang, Yawei Luo, Shuainan Ye, Tan Tang

Abstract

3D fragment reassembly aims to recover the rigid poses of unordered fragment point clouds or meshes in a common object coordinate system to reconstruct the complete shape. The problem becomes particularly challenging as the number of fragments grows, since the target shape is unknown and fragments provide weak semantic cues. Existing end-to-end approaches are prone to cascading failures due to unreliable contact reasoning, most notably inaccurate fragment adjacencies. To address this, we propose Structure-Aware Reassembly (SARe), a generative framework with SARe-Gen for Euclidean-space assembly generation and SARe-Refine for inference-time refinement, with explicit contact modeling. SARe-Gen jointly predicts fracture-surface token probabilities and an inter-fragment contact graph to localize contact regions and infer candidate adjacencies. It adopts a query-point-based conditioning scheme and extracts aligned local geometric tokens at query locations from a frozen geometry encoder, yielding queryable structural representations without additional structural pretraining. We further introduce an inference-time refinement stage, SARe-Refine. By verifying candidate contact edges with geometric-consistency checks, it selects reliable substructures and resamples the remaining uncertain regions while keeping verified parts fixed, leading to more stable and consistent assemblies in the many-fragment regime. We evaluate SARe across three settings, including synthetic fractures, simulated fractures from scanned real objects, and real physically fractured scans. The results demonstrate state-of-the-art performance, with more graceful degradation and higher success rates as the fragment count increases in challenging large-scale reassembly.

SARe: Structure-Aware Large-Scale 3D Fragment Reassembly

Abstract

3D fragment reassembly aims to recover the rigid poses of unordered fragment point clouds or meshes in a common object coordinate system to reconstruct the complete shape. The problem becomes particularly challenging as the number of fragments grows, since the target shape is unknown and fragments provide weak semantic cues. Existing end-to-end approaches are prone to cascading failures due to unreliable contact reasoning, most notably inaccurate fragment adjacencies. To address this, we propose Structure-Aware Reassembly (SARe), a generative framework with SARe-Gen for Euclidean-space assembly generation and SARe-Refine for inference-time refinement, with explicit contact modeling. SARe-Gen jointly predicts fracture-surface token probabilities and an inter-fragment contact graph to localize contact regions and infer candidate adjacencies. It adopts a query-point-based conditioning scheme and extracts aligned local geometric tokens at query locations from a frozen geometry encoder, yielding queryable structural representations without additional structural pretraining. We further introduce an inference-time refinement stage, SARe-Refine. By verifying candidate contact edges with geometric-consistency checks, it selects reliable substructures and resamples the remaining uncertain regions while keeping verified parts fixed, leading to more stable and consistent assemblies in the many-fragment regime. We evaluate SARe across three settings, including synthetic fractures, simulated fractures from scanned real objects, and real physically fractured scans. The results demonstrate state-of-the-art performance, with more graceful degradation and higher success rates as the fragment count increases in challenging large-scale reassembly.
Paper Structure (16 sections, 6 equations, 4 figures, 5 tables)

This paper contains 16 sections, 6 equations, 4 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. 3D Fracture Reassembly.
  4. 3D Diffusion Model.
  5. Diffusion Models with External Representations.
  6. Reassembly Problem Formulation
  7. Method
  8. Query-Point Conditioning
  9. SARe-Gen: Structure-Aware Rectified Flow for Reassembly
  10. SARe-Refine: Inference-Time Structure-Guided Refinement
  11. Experiments
  12. Experimental Setting
  13. Quantitative Evaluations
  14. Qualitative Evaluations.
  15. Ablation Studies and Analyses
  16. ...and 1 more sections

Figures (4)

  • Figure 1: As the fragment count $K$ increases, (a) part accuracy drops and (b) adjacency recall of the induced contact graph decreases accordingly, indicating growing contact-structure errors at larger scales. (c) As an oracle diagnostic, re-inference of RPF conditioned on a small set of GT adjacencies improves an example assembly. All results are computed on the Breaking Bad dataset.
  • Figure 2: Overview of SARe. SARe-Gen generates assembled query points in Euclidean space while predicting fracture-surface tokens and a contact graph. SARe-Refine optionally refines hard cases by keeping reliable substructures fixed and resampling uncertain regions.
  • Figure 3: SARe-Refine pipeline. Filter predicted edges, keep reliable substructures, then RePaint-style resample uncertain regions conditioned on a stable mask.
  • Figure 4: Qualitative results of SARe-Gen and SARe-Refine, along with representative failure cases. (Please zoom in for a clearer view of the geometric details.)