AI Paper Atlas

Research map / Point clouds / Shape and surface completion

RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

Yinyu Nie, Ji Hou, Xiaoguang Han, Matthias Niessner

CVPR 2021 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 76 citations (OpenAlex)

Check 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
jointly train shape prediction with 3D detection (ablation)RfD-Net with VoteNet · ScanNet v2mAP@0.5: 32.63 -> 35.10Improved
jointly train shape prediction with detection (ablation)RfD-Net · ScanNet v2 semantic instance completionmAP (mesh IoU threshold 0.5): 13.94 -> 16.90Improved
jointly train detector and shape generator (ablation)RfD-Net · ScanNet v2 object reconstruction, 16-d3D IoU: 35.75 -> 37.02Improved
jointly train shape prediction with the detector (ablation)RfD-Net with BoxNet · ScanNet v2 3D detectionmAP@0.5: 20.31 -> 22.79Improved
jointly train shape prediction with the detector (ablation)RfD-Net with MLCVNet · ScanNet v2 3D detectionmAP@0.5: 33.40 -> 34.77Improved
jointly train shape prediction with the detector (ablation)RfD-Net with VoteNet+DGCNN · ScanNet v2 3D detectionmAP@0.5: 29.88 -> 32.30Improved
increase input points from 20K to 80K (ablation)RfD-Net · ScanNet v23D Detection: 33.89 -> 35.10Improved
increase input points from 20K to 80K (ablation)RfD-Net · ScanNet v2Instance Completion: 14.39 -> 16.90Improved
set objectness dropout to Nd=30 rather than Nd=10 (ablation)RfD-Net · ScanNet v23D Detection: 35.10 -> 33.37Hurt
set objectness dropout to Nd=30 rather than Nd=10 (ablation)RfD-Net · ScanNet v2Instance Completion: 16.90 -> 14.34Hurt
combine proposal features and point clusters through full skip propagation, including denoising (ablation)RfD-Net · ScanNet v2Instance Completion: 15.42 -> 16.90Improved

Later papers that compared with this method

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

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