AI Paper Atlas

Research map / 3D vision / Face and shape

Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads

Federico Nocentini, Thomas Besnier, Claudio Ferrari, Sylvain Arguillère, Mohamed Daoudi, Stefano Berretti

IJCV 2026 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 4 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 mask and velocity losses (ablation)ScanTalk (md) · VOCAsetFDD: 2.10 -> 1.47Improved
add mask and velocity losses (ablation)ScanTalk (md) · VOCAsetDTW: 1.39 -> 1.14Improved
add mask and velocity losses (ablation)ScanTalk (md) · VOCAsetLVE: 6.38 -> 7.03Hurt
add mask, velocity and cosine losses (ablation)ScanTalk (md) · VOCAsetFDD: 2.10 -> 1.29Improved
add mask, velocity and cosine losses (ablation)ScanTalk (md) · VOCAsetdelta_Cd: 0.60 -> 0.52Improved
add mask, velocity and cosine losses (ablation)ScanTalk (md) · BIWI6LVE: 4.04 -> 4.44Hurt
train on multiple datasets instead of single dataset (ablation)ScanTalk · MultifaceFDD: 64.43 -> 32.20Improved
train on multiple datasets instead of single dataset (ablation)ScanTalk · VOCAsetLVE: 3.01 -> 6.38Hurt
use Chamfer loss instead of MSE on registered data (ablation)ScanTalk · VOCAsetLVE: 6.38 -> 6.57Hurt
train on remeshed data instead of registered (Chamfer loss) (ablation)ScanTalk · VOCAsetFDD: 2.31 -> 8.22Hurt
add Gaussian noise to remeshed data with holes (ablation)ScanTalk · VOCAsetFDD: 9.94 -> 39.0Hurt
random test-time rotation of +-30 degrees around X axis (ablation)ScanTalk · VOCAsetLVE increase (%): 14.9% increase (X) vs 4.8 (Y) and 5.0 (Z)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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