AI Paper Atlas

Research map / 3D vision / Face and shape

Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints

Vikramjit Sidhu, Edgar Tretschk, Vladislav Golyanik, Antonio Agudo, Christian Theobalt

ECCV 2020 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 51 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 the depth control term in the spatial smoothness energy (ablation)N-NRSfM · Synthetic faces traj. Be3D: higher by ~30% without itImproved
tune B=10, K=30, lambda=0, eta=10 instead of defaults (ablation)N-NRSfM · Synthetic faces traj. Ae3D: 0.045 -> 0.032Improved
use K=40 trajectory vectors instead of default K=7 (ablation)N-NRSfM · Synthetic faces traj. Be3D: 0.049 -> 0.0389Improved
replace per-frame FML reconstruction with N-NRSfMN-NRSfM · Actor mocape3D: 0.092 -> 0.0181Improved
use neural N-NRSfM instead of JM on Kinect t-shirtN-NRSfM · Kinect t-shirte3D: 0.0386 -> 0.0309Improved
use neural N-NRSfM instead of JM on Kinect paperN-NRSfM · Kinect papere3D: 0.0338 -> 0.0332Improved
N-NRSfM versus best prior method GMLI on expressionsN-NRSfM · Expressionse3D: 0.026 -> 0.026No clear effect

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