AI Paper Atlas

Research map / Point clouds / Shape and surface completion

ProtoComp: Diverse Point Cloud Completion with Controllable Prototype

Xumin Yu, Yanbo Wang, Jie Zhou, Jiwen Lu

ECCV 2024 · Point clouds › Shape and surface completion · approach: Structure-guided completion · 2 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
use ProtoComp with AdaPoinTr decoderAdaPoinTr · PCN datasetAvg CD-l1 (x1000): 6.53 -> 6.47Improved
wrap decoder with ProtoComp prototype guidancePoinTr · PCN datasetAvg CD-l1 (x1000): 8.38 -> 7.47Improved
complete partial scans with existing completion methodsPCN, SnowFlakeNet, AdaPoinTr · Real-Sensors BenchmarkGD_I (%): 32.8 (partials) vs 27.2 PCNHurt
add text prompt at inferenceProtoComp · Real-Sensors BenchmarkGD_I (%): 33.4 -> 43.6Improved
fine-tune vanilla Point-E directly on 800 pairs (ablation)Model A · Real-Sensors Benchmark (ShapeNet-55 trained)GD_I (%): 57.1 -> 42.9Hurt
add partial condition module (ablation)Model B · Real-Sensors Benchmark (ShapeNet-55 trained)Fidelity-l1 (x1000): 98.4 -> 16.2Improved
use side branch instead of full fine-tuning (ablation)Model C · Real-Sensors Benchmark (ShapeNet-55 trained)GD_I (%): 44.1 -> 45.4Improved
initialize side branch with pre-trained weights (copy) (ablation)Model D · Real-Sensors Benchmark (ShapeNet-55 trained)GD_I (%): 45.4 -> 46.8Improved
reduce training categories from 8 to 4 with same total pairs (ablation)Model E · Real-Sensors Benchmark (ShapeNet-55 trained)GD_I (%): 46.8 -> 42.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 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