AI Paper Atlas

Research map / Detection and segmentation / CNN features

Rescan: Inductive Instance Segmentation for Indoor RGBD Scans

Maciej Halber, Yifei Shi, Kai Xu, Thomas Funkhouser

ICCV 2019 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 14 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 Coverage Term to the objective (ablation)Rescan · Rescan benchmarkInstance Transfer (mean IoU): 0.048 -> 0.650Improved
add Coverage Term to the objective (ablation)Rescan · Rescan benchmarkSemantic Label (mean class IoU): 0.061 -> 0.859Improved
add Coverage Term to the objective (ablation)Rescan · Rescan benchmarkSemantic Instance (mAP@0.5): 0.058 -> 0.837Improved
add Hysteresis Term to the objective (ablation)Rescan · Rescan benchmarkInstance Transfer (mean IoU): 0.226 -> 0.650Improved
add Hysteresis Term to the objective (ablation)Rescan · Rescan benchmarkSemantic Label (mean class IoU): 0.870 -> 0.859Hurt
add Hysteresis Term to the objective (ablation)Rescan · Rescan benchmarkSemantic Instance (mAP@0.5): 0.818 -> 0.837Improved
add Intersection Term to the objective (ablation)Rescan · Rescan benchmarkSemantic Instance (mAP@0.5): 0.781 -> 0.837Improved
add Intersection Term to the objective (ablation)Rescan · Rescan benchmarkInstance Transfer (mean IoU): 0.584 -> 0.650Improved
add Intersection Term to the objective (ablation)Rescan · Rescan benchmarkSemantic Label (mean class IoU): 0.859 -> 0.859No clear effect
add Geometry Term to the objective (ablation)Rescan · Rescan benchmarkInstance Transfer (mean IoU): 0.617 -> 0.650Improved
add Geometry Term to the objective (ablation)Rescan · Rescan benchmarkSemantic Instance (mAP@0.5): 0.825 -> 0.837Improved
add Geometry Term to the objective (ablation)Rescan · Rescan benchmarkSemantic Label (mean class IoU): 0.853 -> 0.859Improved

Later papers that compared with this method

1 later accepted paper reports RESCAN as a baseline in their results tables; 1 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