AI Paper Atlas

Research map / 3D vision / Human pose estimation

Mimic-X: A Large-Scale Motion Dataset via Fast Physics-Based Controller Adaptation

Hongyu Tao, Shuaiying Hou, Junheng Fang, Mingyao Shi, Weiwei Xu

AAAI 2026 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 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 auto-encoder latent space for option policies (ablation)adaptive option framework · Human3.6Mfine-tuning time (min): 12.5 -> 9.0Improved
add auto-encoder latent space (ablation)adaptive option framework · Human3.6MMPJPE: 48.4 -> 33.3Improved
add dynamic-programming option selector (ablation)adaptive option framework · Human3.6MMPJPE: 111.1 -> 33.3Improved
add dynamic-programming option selector (ablation)adaptive option framework · Human3.6Mfine-tuning time (min): 15.5 -> 9.0Improved
add fine-tuning step (ablation)adaptive option framework · Human3.6MMPJPE: 142.6 -> 33.3Improved
use pre-trained option policies instead of training from scratch (ablation)adaptive option framework · Human3.6Mtime per sequence (min): 181.4 -> 9.0Improved
cluster radius 40 instead of 50 (ablation)adaptive option framework · Human3.6MMPJPE: 43.6 -> 33.3Improved
cluster radius 40 instead of 20 (ablation)adaptive option framework · Human3.6Mfine-tuning time (min): 14.5 -> 9.0Improved
use 4x larger single controller instead of clustered policies (ablation)adaptive option framework · Human3.6Mfine-tuning time (min): 9.0 -> 27.1Hurt
train generators on Mimic-X instead of Motion-XT2M-GPT · HumanML3D text-to-motionFID: 0.234 -> 0.190Improved
train generators on Mimic-X instead of Motion-XReMoDiffuse · HumanML3D text-to-motionFID: 0.227 -> 0.158Improved
train generators on Mimic-XT2M-GPT and ReMoDiffuse · HumanML3D text-to-motionR Precision Top3: 0.774 -> 0.775 (T2M-GPT)No clear effect

Earlier methods this paper compares with

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