Skip to yearly menu bar Skip to main content


CurveCloudNet: Processing Point Clouds with 1D Structure

Colton Stearns · Alex Fu · Jiateng Liu · Jeong Joon Park · Davis Rempe · Despoina Paschalidou · Leonidas Guibas

Arch 4A-E Poster #368
[ ]
Fri 21 Jun 5 p.m. PDT — 6:30 p.m. PDT


Modern depth sensors such as LiDAR operate by sweeping laser-beams across the scene, resulting in a point cloud with notable 1D curve-like structures. In this work, we introduce a new point cloud processing scheme and backbone, called CurveCloudNet, which takes advantage of the curve-like structure inherent to these sensors. While existing backbones discard the rich 1D traversal patterns and rely on generic 3D operations, CurveCloudNet parameterizes the point cloud as a collection of polylines (dubbed a "curve cloud"), establishing a local surface-aware ordering on the points. By reasoning along curves, CurveCloudNet captures lightweight curve-aware priors to efficiently and accurately reason in several diverse 3D environments. We evaluate CurveCloudNet on multiple synthetic and real datasets that exhibit distinct 3D size and structure. We demonstrate that CurveCloudNet outperforms both point-based and sparse-voxel backbones in various segmentation settings, notably scaling to large scenes better than point-based alternatives while exhibiting improved single-object performance over sparse-voxel alternatives. In all, CurveCloudNet is an efficient and accurate backbone that can handle a larger variety of 3D environments than past works.

Live content is unavailable. Log in and register to view live content