AI Paper Atlas

Research map / Point clouds / Shape and surface completion

EINet: Point Cloud Completion via Extrapolation and Interpolation

Pingping Cai, Canyu Zhang, LINGJIA SHI, Lili Wang, Nasrin Imanpour, Song Wang

ECCV 2024 · Point clouds › Shape and surface completion · approach: Structure-guided completion · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the Seed Feature Propagation module (coordinate and feature differences) instead of 3-NN propagation (ablation)EINet · PCNCD-L1 (x10^-3): 6.87 -> 6.63Improved
add the feature-space Extrapolation module instead of SnowFlake seed head (ablation)EINet · PCNCD-L1 (x10^-3): 7.02 -> 6.63Improved
add the Mapping Constraint loss (ablation)EINet · PCNCD-L1 (x10^-3): 6.69 -> 6.63Improved
use EINet instead of PoinTr in model sizepoint cloud completion · PCN model complexityparameters (M): 28.9 -> 2.80Improved
use EINet instead of AdaPoinTrpoint cloud completion · PCNCD-L1 (x10^-3): 6.53 -> 6.63Hurt
use EINet instead of AdaPoinTr on ShapeNet-55point cloud completion · ShapeNet-55CD-Avg (CD-L2 x10^-3): 0.81 -> 0.90Hurt
use EINet instead of SeedFormer on PCNpoint cloud completion · PCNCD-L1 (x10^-3): 6.74 -> 6.63Improved

Later papers that compared with this method

2 later accepted papers report EINet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy