Skip to main navigation Skip to search Skip to main content

Beyond Reassembly: Fractured Object Recovery with Missing Parts

  • Qunce Xu
  • , Jiahui Li
  • , Yanpei Cao
  • , Weihao Cheng
  • , Taijiang Mu
  • , Ying Shan
  • , Chuan Li
  • , Da Chen
  • , Yongliang Yang
  • , Shi-Min Hu
  • Tsinghua University
  • Lambda Labs

Research output: Contribution to conference › Paper › peer-review

Abstract

We propose a novel learning-based task named fractured object recovery. Unlike previous fractured object reassembly task that only targets aligning existing parts with overlaps, our task aims to not only reassemble irrelevant parts but also predict missing parts, resulting in a complete shape recovery immediately. Our task coincides with practical experiences, where the prior knowledge of similar shapes can be leverage in the reassembly process, such that even non-overlapping parts can be reasoned into adequate locations. We also present the first learning model for the proposed task by correlating features of both existing and missing parts using a transformer, where the latter is naturally represented as missing tokens. Hence, our model can jointly estimate the poses of the existing parts and predict the shapes of the missing parts. To facilitate the task, we introduce a new dataset based on the existing fractured object benchmark by imposing different configurations of missing parts. We perform extensive evaluations to demonstrate the performance of the proposed model over baselines. The results show that joint part reassembly and prediction can be made possible and also have mutual benefits, which we believe can inspire future research and favor real applications.
Original languageEnglish
Publication statusPublished - 3 Jun 2026
EventThe IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 -
Duration: 3 Jun 2026 → 7 Jun 2026
https://cvpr.thecvf.com/

Conference

ConferenceThe IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026
Abbreviated titleCVPR 2026
Period3/06/26 → 7/06/26
Internet address

Fingerprint

Dive into the research topics of 'Beyond Reassembly: Fractured Object Recovery with Missing Parts'. Together they form a unique fingerprint.

Cite this