AnchorComplete: Recovering Complete Scene Meshes from Partial Point Clouds

Weirong Chen, Ismail ElYamany, Ganlin Zhang, Chuanxia Zheng, Andrea Vedaldi, Daniel Cremers

AnchorComplete: Recovering Complete Scene Meshes from Partial Point Clouds: 9 upvotes on Hugging Face Daily Papers, #22 of 38 papers on 2026-11-05. Day-by-day upvote history.

Upvotes over time

It had 9 upvotes by its first day, 9 upvotes by the next day, 11 upvotes by day 3, 9 upvotes by day 7, and has 9 now. It ranked #117 of 207 papers in its week and #177 of 340 in its month.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.