cs.CVNov 2, 2026

AnchorComplete: Recovering Complete Scene Meshes from Partial Point Clouds

Authors: Weirong Chen, Ismail El-Yamany, Ganlin Zhang, Chuanxia Zheng, Andrea Vedaldi, Daniel Cremers

Organizations: Technical University of Munich · Munich Center for Machine Learning · Nanyang Technological University · University of Oxford

Abstract

Most image-based 3D reconstructors primarily recover visible surfaces, producing partial point clouds with large holes and leaving unobserved geometry unresolved. To address this limitation, we introduce AnchorComplete, a framework that reconstructs complete scene meshes from partial point clouds while preserving observed geometry and supporting scenes of varying scales. Building on TRELLIS.2, our method combines partial-point conditioning, which integrates global scene tokens with local spatial evidence to anchor generation to the input, and metric-scale coarse-to-fine generation, which progressively refines scene geometry within fixed-size windows while maintaining global structural consistency. Experiments on Replica and SCRREAM demonstrate that AnchorComplete consistently outperforms strong baselines in complete-scene reconstruction, particularly under sparse-view settings.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World

    Oct 13, 2026Mengchen Zhang, Yang Li, Chunshi Wang +23D Reconstruction3D Mesh Reconstruction

  2. ScaleBlind: Point Cloud Completion under Unknown Scale

    Sep 20, 2026Shenghui Wu, Chen Wang, Yuan Feng +3Point Cloud Completion

  3. Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow

    Mar 30, 2026Quan Meng, Yujin Chen, Lei Li +23D Scene Completion3D Scene Generation