RAM: Recover Any 3D Human Motion in-the-Wild
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914462539186176 |
|---|---|
| author | Jia, Sen Zhu, Ning Zhong, Jinqin Zhou, Jiale Zhang, Huaping Hwang, Jenq-Neng Li, Lei |
| author_facet | Jia, Sen Zhu, Ning Zhong, Jinqin Zhou, Jiale Zhang, Huaping Hwang, Jenq-Neng Li, Lei |
| contents | RAM incorporates a motion-aware semantic tracker with adaptive Kalman filtering to achieve robust identity association under severe occlusions and dynamic interactions. A memory-augmented Temporal HMR module further enhances human motion reconstruction by injecting spatio-temporal priors for consistent and smooth motion estimation. Moreover, a lightweight Predictor module forecasts future poses to maintain reconstruction continuity, while a gated combiner adaptively fuses reconstructed and predicted features to ensure coherence and robustness. Experiments on in-the-wild multi-person benchmarks such as PoseTrack and 3DPW, demonstrate that RAM substantially outperforms previous state-of-the-art in both Zero-shot tracking stability and 3D accuracy, offering a generalizable paradigm for markerless 3D human motion capture in-the-wild. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19929 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RAM: Recover Any 3D Human Motion in-the-Wild Jia, Sen Zhu, Ning Zhong, Jinqin Zhou, Jiale Zhang, Huaping Hwang, Jenq-Neng Li, Lei Computer Vision and Pattern Recognition Artificial Intelligence RAM incorporates a motion-aware semantic tracker with adaptive Kalman filtering to achieve robust identity association under severe occlusions and dynamic interactions. A memory-augmented Temporal HMR module further enhances human motion reconstruction by injecting spatio-temporal priors for consistent and smooth motion estimation. Moreover, a lightweight Predictor module forecasts future poses to maintain reconstruction continuity, while a gated combiner adaptively fuses reconstructed and predicted features to ensure coherence and robustness. Experiments on in-the-wild multi-person benchmarks such as PoseTrack and 3DPW, demonstrate that RAM substantially outperforms previous state-of-the-art in both Zero-shot tracking stability and 3D accuracy, offering a generalizable paradigm for markerless 3D human motion capture in-the-wild. |
| title | RAM: Recover Any 3D Human Motion in-the-Wild |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.19929 |