AI Paper Atlas

Research map / 3D vision / 3D generation

Motion-2-to-3: Leveraging 2D Motion Data for 3D Motion Generations

Ruoxi Guo, Huaijin Pi, Zehong Shen, Qing Shuai, Zechen Hu, Zhumei Wang, Yajiao Dong, Ruizhen Hu, Taku Komura, Sida Peng, Xiaowei Zhou

ICCV 2025 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 12 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 2D motion pretraining of the generator before multi-view fine-tuning (ablation)Multi-view diffusion model · HumanML3D (model design ablation)FID: 4.950 -> 0.321Improved
add consistency block (triangulate and reproject at each diffusion step) (ablation)Multi-view diffusion model · HumanML3D (model design ablation)FID: 0.321 -> 0.642Hurt
use 3 views instead of 4 (ablation)Multi-view diffusion model · HumanML3D (model design ablation)FID: 0.321 -> 0.654Hurt
use 5 views instead of 4 (ablation)Multi-view diffusion model · HumanML3D (model design ablation)FID: 0.321 -> 0.593Hurt
use multi-view attention generation instead of lifting generated 2D with MotionBERT (ablation)2D motion generator · HumanML3D (data utilization ablation)FID: 23.292 -> 0.321Improved
use multi-view diffusion with consistency learned from 3D data instead of MAS (ablation)2D motion generator · HumanML3D (data utilization ablation)FID: 11.893 -> 0.321Improved
use root-decoupled multi-view generation instead of 2D-condition multi-view model (ablation)2D motion generator · HumanML3D (data utilization ablation)FID: 0.877 -> 0.321Improved
use 2D video motion then 3D fine-tuning instead of monocular 3D annotations (Motion-X++) (ablation)text-to-motion model · HumanML3D (data utilization ablation)FID: 0.893 -> 0.321Improved
use 2D motion pretraining and multi-view 3D fine-tuning versus 3D-only MDMtext-to-motion model · HumanML3DFID: 0.544 -> 0.321Improved
use our method versus MLDtext-to-motion model · HumanML3DR-Precision (top-3): 0.772 -> 0.697Hurt
use our method versus MDMtext-to-motion model · HumanML3DDiversity: 9.559 -> 9.286Hurt
use our method versus MDM on novel texttext-to-motion model · Novel text prompts (user study)Best Motion Rate: 24.08% -> 51.43%Improved

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