AI Paper Atlas

Research map / Video / Video generation

Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion

Dongseok Shim, Julian Tanke, Kengo Uchida, christian simon, Koichi Saito, Takashi Shibuya, Shusuke Takahashi, Yuki Mitsufuji

ECCV 2026 · Video › Video generation · approach: Text-to-motion diffusion · 0 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 ground-truth shape conditioning (gender and beta) instead of canonical body (ablation)Odoriko · HumanML3DFID: 0.592 -> 0.103Improved
add ground-truth shape conditioning instead of canonical body (ablation)Odoriko · HumanML3DR-Precision Top-3: 0.768 -> 0.805Improved
use predicted gender and beta rather than neutral gender (ablation)Odoriko · EMDB (24)MPJPE: 76.3 -> 70.2Improved
use predicted beta rather than zero beta (ablation)Odoriko · EMDB (24)MPJPE: 72.7 -> 70.2Improved
use ground-truth shape instead of estimated shape (ablation)Odoriko · EMDB (24)MPJPE: 70.2 -> 70.0No clear effect
add camera-centric local root orientation (ablation)Odoriko · EMDB (24)MPJPE: 285.9 -> 70.2Improved
add 2D keypoint input (ablation)Odoriko · 3DPW (14)MPJPE: 100.2 -> 69.9Improved
add 2D keypoint input (ablation)Odoriko · EMDB (24)MPJPE: 71.1 -> 70.2No clear effect
increase UniPC denoising steps from 1 to 25 (ablation)Odoriko · HumanML3DFID: 1.804 -> 0.103Improved
increase UniPC steps from 25 to 50 (ablation)Odoriko · HumanML3DFID: 0.103 -> 0.113No clear effect
use UniPC sampler instead of DDIM at 25 steps (ablation)Odoriko · HumanML3DFID: 0.107 -> 0.103No clear effect
add CLIP global feature (ablation)Odoriko · HumanML3DR-Precision Top-3: 0.799 -> 0.805Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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