AI Paper Atlas

Research map / 3D vision / Face and shape

Unsupervised Volumetric Animation

Aliaksandr Siarohin, Willi Menapace, Ivan Skorokhodov, Kyle Olszewski, Jian Ren, Hsin-Ying Lee, Menglei Chai, Sergey Tulyakov

CVPR 2023 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 21 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
use PnP-based pose prediction rather than directly predicting part poses (ablation)UVA, geometry phase · VoxCelebAYD: 0.707 -> 0.141Improved
use PnP-based pose prediction rather than directly predicting part poses (ablation)UVA, geometry phase · VoxCelebASC: 0.160 -> 0.113Improved
add the unsupervised background loss (ablation)UVA, geometry phase · VoxCelebAYD: 0.301 -> 0.141Improved
add geometry pretraining before introducing multiple parts (ablation)UVA, 10 parts · VoxCelebAYD: 1.08 -> 0.051Improved
use five source frames instead of oneUVA · VoxCelebAYD: 0.051 -> 0.045Improved
use five source frames instead of oneUVA · VoxCelebL1: 0.0655 -> 0.0418Improved
use five source frames instead of oneUVA · TEDXPeopleAYD: 0.128 -> 0.107Improved
use five source frames instead of oneUVA · TEDXPeopleL1: 0.0474 -> 0.029Improved
use five source frames instead of oneUVA · VoxCeleb novel view synthesisASC: 0.119 -> 0.126Hurt
use five source frames instead of oneUVA · VoxCeleb novel view synthesisAPC: 0.171 -> 0.184Hurt
learn geometry and parts from monocular data without camera supervisionUVA · VoxCelebdepth correlation: 0.53 -> 0.63Improved
learn geometry from real-image training data rather than use the general-purpose depth predictorUVA · Synthetic facesdepth correlation: 0.602 -> 0.793Improved

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