mlsanityData to 14 Oct 2026

KASportsFormer: Kinematic Anatomy Enhanced Transformer for 3D Human Pose Estimation on Short Sports Scene Video

arXiv 2507.20763 ↗First posted 28 Jul 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent transformer based approaches have demonstrated impressive performance in solving real-world 3D human pose estimation problems. Albeit these approaches achieve fruitful results on benchmark datasets, they tend to fall short of sports scenarios where human movements are more complicated than daily life actions, as being hindered by motion blur, occlusions, and domain shifts. Moreover, due to the fact that critical motions in a sports game often finish in moments of time (e.g., shooting), the ability to focus on momentary actions is becoming a crucial factor in sports analysis, where current methods appear to struggle with instantaneous scenarios. To overcome these limitations, we introduce KASportsFormer, a novel transformer based 3D pose estimation framework for sports that incorporates a kinematic anatomy-informed feature representation and integration module. In which the inherent kinematic motion information is extracted with the Bone Extractor (BoneExt) and Limb Fuser (LimbFus) modules and encoded in a multimodal manner. This improved the capability of comprehending sports poses in short videos. We evaluate our method through two representative sports scene datasets: SportsPose and WorldPose. Experimental results show that our proposed method achieves state-of-the-art results with MPJPE errors of 58.0mm and 34.3mm, respectively. Our code and models are available at: https://github.com/jw0r1n/KASportsFormer

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 50 references that are in the map. First posted on arXiv 28 Jul 2025.

Builds on

30 of 50 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  3. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  4. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  5. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  6. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 274
  7. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  8. 2017Integral Human Pose Regressioncited by 256
  9. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  10. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 193
  11. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  12. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
18 more
  1. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  2. 2023Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregationcited by 82
  3. 2019XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Cameracited by 68
  4. 2021Direct Multi-view Multi-person 3D Pose Estimationcited by 64
  5. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 64
  6. 2020AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wildcited by 40
  7. 2022Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Informationcited by 31
  8. 2023SportsPose -- A Dynamic 3D sports pose datasetcited by 26
  9. 2024FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Modelscited by 23
  10. 2022Learnable human mesh triangulation for 3D human pose and shape estimationcited by 16
  11. 2024AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movementscited by 15
  12. 2025AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movementscited by 14
  13. 2020HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimationcited by 12
  14. 2024Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Networkcited by 12
  15. 2023Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Drivingcited by 8
  16. 20243D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approachcited by 7
  17. 2024BLAPose: Enhancing 3D Human Pose Estimation with Bone Length Adjustmentcited by 2
  18. 2024Multi-hop graph transformer network for 3D human pose estimationcited by 1

Built on by

Not cited yet.