AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Deep Loss Convexification for Learning Iterative Models

Ziming Zhang, Youjia Shao, Yiqing Zhang, Fangzhou Lin, Haichong K. Zhang, Elke Angelika Rundensteiner

TPAMI 2024 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 10 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 DLC to LSTM trainingLSTM · Pixel-MNISTaccuracy: 98.2 -> 99.50Improved
add DLC to DCPDCP · ModelNet40 unseen classes (w/o ICP)MSE(Euler): 6.8747 -> 1.0836Improved
add DLC to PRNetPRNet · ModelNet40 unseen classes (w/o ICP)MSE(Euler): 20.3915 -> 11.3448Improved
add DLC to DCPDCP · ModelNet40 unseen classes (w/o ICP)MSE(T): 1.79e-5 -> 2.55e-5Hurt
add DLC to PRNetPRNet · 3DMatch unseen (w/o ICP)MSE(Euler): 1104.9437 -> 294.2320Improved
add DLC to PRNetPRNet · 3DMatch unseen (with ICP)MSE(T): 0.2076 -> 0.0021Improved
add ICP refinement to DLC+DCPDLC+DCP · ModelNet40 unseen classesMSE(Euler): 1.0836 -> 0.1705Improved
add DLC to PRNet pretrained on ModelNet40PRNet · ShapeNetCore unseen class 14 (w/o ICP)MSE(Euler): 2.0465 -> 1.0666Improved
add DLC to PRNet pretrained on ModelNet40PRNet · ShapeNetCore all classes (w/o ICP)MSE(Euler): 13.6229 -> 15.3662Hurt
add hinge-loss constraints (star-convexity) to LK loss (ablation)DeepLK · Google Earth multimodal alignmentoverfitting / pixel errorImproved
add all three constraints versus subsets (ablation)DLC-DeepLK · Google Earth multimodal alignmentsuccess rateImproved
increase rho from small to large (ablation)DLC-DeepLK · Google Earth multimodal alignmentpixel errorImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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