AI Paper Atlas

Research map / 3D vision / Face and shape

Sparse to Dense Dynamic 3D Facial Expression Generation

Naima Otberdout, Claudio Ferrari, Mohamed Daoudi, Stefano Berretti, Alberto Del Bimbo

CVPR 2022 · 3D vision › Face and shape · approach: Speech-driven 3D facial animation · 31 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 S2D-Dec instead of PCA-2203D facial expression reconstruction · CoMA expression splitmean per-vertex error (mm): 0.76 \pm 0.73 -> 0.52 \pm 0.59Improved
Use S2D-Dec instead of PCA-2203D facial expression reconstruction · D3DFACS expression splitmean per-vertex error (mm): 0.42 \pm 0.44 -> 0.28\pm 0.31Improved
Use S2D-Dec instead of PCA-2203D facial expression reconstruction · CoMA identity splitmean per-vertex error (mm): 0.80 \pm 0.73 -> 0.55 \pm 0.62Improved
Use S2D-Dec instead of PCA-2203D facial expression reconstruction · D3DFACS identity splitmean per-vertex error (mm): 0.56 \pm 0.56 -> 0.27 \pm 0.30Improved
Generate landmark motion with Motion3DGAN instead of LSTMCoMA dynamic expression generation · CoMA expression classification, Gen-LMclassification accuracy (%): 46.53 -> 65.28Improved
Generate landmark motion with Motion3DGAN instead of LSTMCoMA dynamic expression generation · CoMA expression classification, Det-LMclassification accuracy (%): 52.08 -> 69.44Improved
Generate landmark motion with Motion3DGAN instead of LSTMCoMA dynamic expression generation · CoMA expression generation, Gen-LMFID: 21.76 -> 20.45Improved
Generate landmark motion with Motion3DGAN instead of LSTMCoMA dynamic expression generation · CoMA expression generation, Det-LMFID: 27.96 -> 19.01Improved
Add standard L1 reconstruction loss without landmark-distance weights (ablation)S2D-Dec · CoMA reconstruction ablationmean per-vertex error (mm): 1.27 \pm 1.88 -> 0.92 \pm 1.33Improved
Add landmark-distance weights to the L1 reconstruction loss (ablation)S2D-Dec · CoMA reconstruction ablationmean per-vertex error (mm): 0.92 \pm 1.33 -> 0.50\pm 0.56Improved

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