AI Paper Atlas

Research map / 3D vision / Face and shape

Neural Deformation Graphs for Globally-Consistent Non-Rigid Reconstruction

Aljaz Bozic, Pablo Palafox, Michael Zollhofer, Justus Thies, Angela Dai, Matthias Niessner

CVPR 2021 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 72 citations (OpenAlex)

Check 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 affinity consistency and sparsity losses (ablation)Neural Deformation Graph (GRAPH) · DeformingThings4D synthetic sequencesChamfer (× 10^-4): 0.50 -> 0.46Improved
Add affinity consistency and sparsity losses (ablation)Neural Deformation Graph (GRAPH) · DeformingThings4D synthetic sequencesEPE3D (× 10^-2): 8.93 -> 8.03Improved
Add viewpoint consistency (ablation)Neural Deformation Graph with affinity optimization · DeformingThings4D synthetic sequencesChamfer (× 10^-4): 0.46 -> 0.44Improved
Add viewpoint consistency (ablation)Neural Deformation Graph with affinity optimization · DeformingThings4D synthetic sequencesEPE3D (× 10^-2): 8.03 -> 4.12Improved
Add surface consistency (ablation)Neural Deformation Graph with affinity optimization and viewpoint consistency · DeformingThings4D synthetic sequencesChamfer (× 10^-4): 0.44 -> 0.40Improved
Add surface consistency (ablation)Neural Deformation Graph with affinity optimization and viewpoint consistency · DeformingThings4D synthetic sequencesEPE3D (× 10^-2): 4.12 -> 1.16Improved
Add pose conditioning to local surface MLPs (ablation)Neural Deformation Graph · DeformingThings4D synthetic sequencesChamfer (× 10^-4): 0.46 -> 0.40Improved
Use Neural Deformation Graph instead of SIFDeformingThings4D synthetic sequences · DeformingThings4D synthetic sequencesChamfer (× 10^-4): 1.12 -> 0.40Improved
Use Neural Deformation Graph instead of Multiview DynamicFusionDeformingThings4D synthetic sequences · DeformingThings4D synthetic sequencesEPE3D (× 10^-2): 3.06 -> 1.16Improved

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