AnchorComplete recovers complete scene meshes from partial point clouds
Original title: AnchorComplete: Recovering Complete Scene Meshes from Partial Point Clouds
AnchorComplete reconstructs complete scene meshes from partial point clouds using partial-point conditioning and metric-scale coarse-to-fine generation.
AnchorComplete addresses large holes in visible-surface reconstructions by combining partial-point conditioning with global scene tokens and local spatial evidence. It supports varying scene scales and preserves observed geometry. Experiments on Replica and SCRREAM show consistent outperformance over baselines under sparse-view settings.
- Integrates global scene tokens with local evidence
- Metric-scale coarse-to-fine generation
- Preserves observed geometry
- Outperforms strong baselines on Replica and SCRREAM
- Built on TRELLIS.2
- AI models
- AnchorComplete
From the original article
1 min read at huggingface.co
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.
By Weirong Chen, Ismail El-Yamany, Ganlin Zhang · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.