Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

POCO: Point Convolution for Surface Reconstruction

About

Implicit neural networks have been successfully used for surface reconstruction from point clouds. However, many of them face scalability issues as they encode the isosurface function of a whole object or scene into a single latent vector. To overcome this limitation, a few approaches infer latent vectors on a coarse regular 3D grid or on 3D patches, and interpolate them to answer occupancy queries. In doing so, they loose the direct connection with the input points sampled on the surface of objects, and they attach information uniformly in space rather than where it matters the most, i.e., near the surface. Besides, relying on fixed patch sizes may require discretization tuning. To address these issues, we propose to use point cloud convolutions and compute latent vectors at each input point. We then perform a learning-based interpolation on nearest neighbors using inferred weights. Experiments on both object and scene datasets show that our approach significantly outperforms other methods on most classical metrics, producing finer details and better reconstructing thinner volumes. The code is available at https://github.com/valeoai/POCO.

Alexandre Boulch, Renaud Marlet• 2022

Related benchmarks

TaskDatasetResultRank
3D ReconstructionShapeNet (test)--
74
3D Geometry ReconstructionScanNet--
54
3D surface reconstructionShapeNet 12 (test)
CD10.3
24
Scene-level 3D ReconstructionScanNet (test)
F-score79
20
Scene ReconstructionSceneNet (test)
Chamfer Distance (CD)0.53
16
Surface ReconstructionShapeNet (test)
CDL10.03
11
3D surface reconstructionCerebral 75
Chamfer Distance (CD)0.36
10
3D surface reconstructionCoronaries 75
Chamfer Distance (CD)0.72
10
3D surface reconstructionHeart 100
Chamfer Distance2.7
10
3D surface reconstructionPulmonary 75
CD2
10
Showing 10 of 35 rows

Other info

Code

Follow for update