AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Few ‘Zero Level Set’-Shot Learning of Shape Signed Distance Functions in Feature Space

Amine Ouasfi, Adnane Boukhayma

ECCV 2022 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction · 19 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 meta-learning in feature space (few-shot adaptation of decoder)IF-Nets · ShapeNet multi-class (3000 pts, 128^3)IoU: 0.88 -> 0.91Improved
add meta-learning in feature spaceIF-Nets · ShapeNet multi-class (300 pts, 32^3)IoU: 0.67 -> 0.74Improved
add meta-learning in feature spaceIF-Nets · FAUST (trained on ShapeNet)IoU: 0.82 -> 0.84Improved
add meta-learning (vs Ours w/o meta learn.) (ablation)Ours · ShapeNet table class (300 pts, 32^3)IoU: 0.58 -> 0.66Improved
add meta-learning (ablation)Ours · ShapeNet table class (3000 pts, 128^3)IoU: 0.82 -> 0.87Improved
add meta-learning on noisy input points (ablation)Ours · ShapeNet table class (3000 pts, 128^3, noisy)IoU: 0.85 -> 0.87Improved
initialize meta-decoder from pre-trained base model (ablation)Ours · ShapeNet table class (3000 pts, 128^3)IoU: 0.86 -> 0.87Improved
initialize meta-decoder from pre-trained base model (ablation)Ours · ShapeNet table class (300 pts, 128^3)CD2 (x1e-3): 0.203 -> 0.082Improved
tune the encoder during meta-learning (ablation)Ours · ShapeNet table class (3000 pts, 128^3)IoU: 0.87 -> 0.86No clear effect
reduce input resolution from 128^3 to 32^3 (3000 pts)Ours vs IF-Nets · ShapeNet table classIoU: Ours drops roughly 14% vs 20% for IF-NetsMixed
reduce input to 300 pts at 32^3 on multi-classOurs vs IF-Nets · ShapeNet multi-classIoU: Ours drops 18% vs 23% for IF-NetsMixed
add meta-learning inferenceOurs · inference timelatency: 60 ms -> 150 msHurt

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