atlas

Research map / Point clouds / Shape and surface completion

DeepCurrents: Learning Implicit Representations of Shapes With Boundaries

CVPR 2022 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction · 21 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 DeepCurrents instead of the baseline reconstruction methodSingle-surface reconstruction · FAUST headUCD: 0.0049 -> 0.0010Helped
Use DeepCurrents instead of the baseline reconstruction methodSingle-surface reconstruction · FAUST handUCD: 0.0045 -> 0.0011Helped
Use DeepCurrents instead of the baseline reconstruction methodSingle-surface reconstruction · FAUST torsoUCD: 0.0049 -> 0.00092Helped
Use DeepCurrents instead of the baseline reconstruction methodSingle-surface reconstruction · FAUST footUCD: 0.0055 -> 0.00092Helped
Add random Fourier feature input projection (ablation)DeepCurrents surface reconstruction · FAUST handlearnabilityHelped
Add the surface loss term (ablation)DeepCurrents surface reconstruction · FAUST handsurface recoveryHelped
Add boundary weighting to the current loss (ablation)DeepCurrents surface reconstruction · FAUST handboundary sharpnessHelped
Use softplus instead of ReLU activations (ablation)DeepCurrents decoder · FAUST handsurface sharpnessHelped

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