Papers › CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation
CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation
Mohammed Hassanin, Abdelwahed Khamiss, Mohammed Bennamoun, Farid Boussaid, Ibrahim Radwan
3D human pose estimation can be handled by encoding the geometric dependencies between the body parts and enforcing the kinematic constraints. Recently, Transformer has been adopted to encode the long-range dependencies between the joints in the spatial and temporal domains. While they had shown excellence in long-range dependencies, studies have noted the need for improving the locality of vision Transformers. In this direction, we propose a novel pose estimation Transformer featuring rich representations of body joints critical for capturing subtle changes across frames (i.e., inter-feature representation). Specifically, through two novel interaction modules; Cross-Joint Interaction and Cross-Frame Interaction, the model explicitly encodes the local and global dependencies between the body joints. The proposed architecture achieved state-of-the-art performance on two popular 3D human pose estimation datasets, Human3.6 and MPI-INF-3DHP. In particular, our proposed CrossFormer method boosts performance by 0.9% and 0.3%, compared to the closest counterpart, PoseFormer, using the detected 2D poses and ground-truth settings respectively.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Human Pose Estimation | Human3.6M | CrossFormer (T=81) | Average MPJPE (mm) | 43.7 | #30 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | CrossFormer (T=81) | Multi-View or Monocular | Monocular | #30 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | CrossFormer (T=81) | Using 2D ground-truth joints | No | #30 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | MPI-INF-3DHP | CrossFormer | AUC | 57.5 | #34 of 108 | Archive leaderboard | report |
| 3D Human Pose Estimation | MPI-INF-3DHP | CrossFormer | MPJPE | 76.3 | #34 of 108 | Archive leaderboard | report |
| 3D Human Pose Estimation | MPI-INF-3DHP | CrossFormer | PCK | 89.1 | #34 of 108 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections