AI Paper Atlas

Research map / 3D vision / Face and shape

f-SfT: Shape-From-Template With a Physics-Based Deformation Model

Navami Kairanda, Edith Tretschk, Mohamed Elgharib, Christian Theobalt, Vladislav Golyanik

CVPR 2022 · 3D vision › Face and shape · approach: Pixel-aligned implicit human and hand reconstruction · 23 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
Use a physics-based deformation model with differentiable renderingSfT reconstruction · φ-SfT real datasetChamfer distance (×10⁴): 3.93 vs 5.92*Improved
Add internal stretching and bending forces and material parameters instead of using only corrective forces (ablation)φ-SfT · φ-SfT real datasetChamfer distance (×10⁴): 6.77 -> 4.48Improved
Add corrective forces 𝓕 (ablation)φ-SfT · φ-SfT real datasetChamfer distance (×10⁴): 10.69 -> 4.48Improved
Use adaptive temporal-window training rather than activating all frames from the start (ablation)φ-SfT · φ-SfT real datasetChamfer distance (×10⁴): 6.21 -> 4.48Improved
Add silhouette energy E_s (ablation)φ-SfT · φ-SfT real datasetChamfer distance (×10⁴): 5.33 -> 4.48Improved

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