AI Paper Atlas

Research map / 3D vision / Face and shape

Neural Non-Rigid Tracking

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

NeurIPS 2020 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 22 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 graph and warp losses backpropagated through differentiable solver (ablation)Correspondence network · DeepDeform trackingEPE 3D (mm): 44.05 -> 36.96Improved
Add self-supervised correspondence weighting (ablation)Phi_c+g+w · DeepDeform trackingGraph Error 3D (mm): 54.24 -> 31.00Improved
Use self-supervised instead of supervised (BCE) weighting (ablation)Phi_c+g+w · DeepDeform trackingEPE 3D (mm): 27.42 -> 26.29Improved
Add supervised weighting to correspondence-loss-only model (ablation)Phi_c · DeepDeform trackingEPE 3D (mm): 44.05 -> 28.95Improved
Use full end-to-end method instead of Phi_c only (ablation)Reconstruction pipeline · DeepDeform reconstructiondeformation error (mm): 54.85 -> 28.72Improved
Use bilinear instead of nearest-neighbor depth sampling (ablation)Solver · DeepDeform trackingEPE 3D: 5.8% lower EPE 3DImproved
Use ARAP edge re-weighting (ablation)Solver · DeepDeform trackingEPE 3D: 0.8% lower EPE 3DNo clear effect
Use coarser deformation graph (15 cm instead of 5 cm node coverage) (ablation)Solver · DeepDeform trackingGraph Error 3D: 28.46% higher Graph Error 3DHurt
Unroll 3 Gauss-Newton iterations instead of 1 (ablation)Solver · DeepDeform trackingEPE 3D: 24.9% lower EPE 3DImproved
Use 4 Gauss-Newton iterations instead of 3 (ablation)Solver · DeepDeform trackingEPE 3D: 0.04% lower EPE 3DNo clear effect
Denser keyframes (every 50 instead of 100 frames) (ablation)Reconstruction pipeline · DeepDeform reconstructiondeformation error (mm): 30.70 -> 28.72Improved
Replace DeepDeform sparse correspondence network with dense PWC-Net based predictionNon-rigid reconstruction · DeepDeform reconstructionruntime per keyframe (ms): 2299 -> 27Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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