AI Paper Atlas

Research map / 3D vision / Human pose estimation

DiffusionPose: Markov-Optimized Diffusion Model for Human Pose Estimation

Zhigang Wang, Zhenguang Liu, Shaojing Fan, Sifan Wu, Yingying Jiao

AAAI 2026 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 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 Spatio-Temporal Feature Encoder (Mamba plus Transformer) to the ViT plus U-Net baseline (ablation)ViT + U-Net baseline · PoseTrack2017 valmAP: 81.2 -> 85.7Improved
replace U-Net with the Markov-based Pose Denoising Decoder (ablation)ViT baseline · PoseTrack2017 valmAP: 81.2 -> 86.1Improved
use both Spatio-Temporal Feature Encoder and Pose Denoising Decoder together (ablation)DiffusionPose · PoseTrack2017 valmAP: 81.2 -> 87.8Improved
use Spatio-Temporal Block (Mamba plus attention) instead of vanilla Transformer block (ablation)Spatio-Temporal Feature Encoder · PoseTrack2017 valmAP: 86.3 -> 87.8Improved
add vanilla Transformer block to encoder over no encoder (ablation)DiffusionPose · PoseTrack2017 valmAP: 86.1 -> 86.3No clear effect
add feature conditions Cf with cross-attention in the decoder (ablation)Pose Denoising Decoder · PoseTrack2017 valmAP: 85.7 -> 86.0Improved
add position conditions Cp with location-guide self-attention (ablation)Pose Denoising Decoder · PoseTrack2017 valmAP: 86.0 -> 86.5Improved
add Markov Optimization Layer (MRF message passing between joints) (ablation)Pose Denoising Decoder · PoseTrack2017 valmAP: 86.5 -> 87.2Improved
add Markov loss on limb length and angle (ablation)DiffusionPose · PoseTrack2017 valmAP: 87.2 -> 87.8Improved
use DiffusionPose instead of DiffPose on occlusion and fast-motion videosDiffusionPose · Challenging-PoseTrackmAP: 55.3 -> 59.7Improved
use single-step DDIM denoising at inference with DiffusionPoseDiffusionPose · PoseTrack2017 valconvergence and accuracy: converges within 10 epochs vs 30 for DiffPoseImproved

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