AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Parametrizing Product Shape Manifolds by Composite Networks

Josua Sassen, Klaus Hildebrandt, Martin Rumpf, Benedikt Wirth

ICLR 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Equivariant and disentangled latent representations · 0 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
Use a composite factorwise MLP plus convolutional combination network instead of a monolithic networkFreaky Torus parametrization · Freaky TorusR²: 0.95 -> 0.99Improved
Use a composite network instead of affine combinationSPGA shape manifolds · SMPL+XR²: 0.78 -> 0.93Improved
Use a composite network instead of a monolithic networkSPGA shape manifolds · SMPL+XR²: 0.85 -> 0.93Improved
Use a composite network instead of affine combinationSPGA shape manifolds · SCAPER²: 0.77 -> 0.91Improved
Use a composite network instead of a monolithic networkSPGA shape manifolds · SCAPER²: 0.60 -> 0.91Improved
Use a composite network instead of affine combinationSPGA shape manifolds · HandsR²: 0.88 -> 0.98Improved
Use a composite network instead of a monolithic networkSPGA shape manifolds · HandsR²: 0.95 -> 0.98Improved
Use a composite network instead of affine combinationSPGA shape manifolds · FacesR²: 0.96 -> 0.99Improved
Use a composite network instead of a monolithic networkSPGA shape manifolds · FacesR²: 0.95 -> 0.99Improved
Use a composite network instead of the prior methodSPGA shape manifolds · HandsR²: 0.80 -> 0.98Improved
Use a composite network instead of the prior methodSPGA shape manifolds · FacesR²: 0.95 -> 0.99Improved
Reduce training data to 20% of the full training setComposite network · SCAPER²: 0.91 -> 0.86Hurt

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