AI Paper Atlas

Research map / 3D vision / 3D generation

Synthesis of Compositional Animations From Textual Descriptions

Anindita Ghosh, Noshaba Cheema, Cennet Oguz, Christian Theobalt, Philipp Slusallek

ICCV 2021 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 186 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 joint training of the embedding space (ablation)two-stream hierarchical model · KIT Motion-Languageuser preference scoreImproved
add two-stream upper/lower body representation (ablation)hierarchical model · KIT Motion-Languageuser preference scoreImproved
add extra losses beyond pose prediction loss (ablation)two-stream hierarchical model · KIT Motion-Languageuser preference scoreImproved
add selected BERT layers instead of Word2Vec (ablation)text encoder · KIT Motion-Languageuser preference scoreImproved
replace JL2P with the proposed hierarchical two-stream modelJL2P · KIT Motion-Languagemean APE: improvement of 55.4% in the mean APEImproved
replace Lin et al. with the proposed modelLin et al. · KIT Motion-LanguageSEE: 83.1% in CEE and SEEImproved

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