Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.21234 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911024335028224 |
|---|---|
| author | Cui, Qifei Zhou, Yuang Deng, Ruichen |
| author_facet | Cui, Qifei Zhou, Yuang Deng, Ruichen |
| contents | This paper presents ESFP, an end-to-end pipeline that converts monocular RGB video into executable joint trajectories for a low-cost 4-DoF desktop arm. ESFP comprises four sequential modules. (1) Estimating: ROMP lifts each frame to a 24-joint 3-D skeleton. (2) Smoothing: the proposed HPSTM-a sequence-to-sequence Transformer with self-attention-combines long-range temporal context with a differentiable forward-kinematics decoder, enforcing constant bone lengths and anatomical plausibility while jointly predicting joint means and full covariances. (3) Filtering: root-normalized trajectories are variance-weighted according to HPSTM's uncertainty estimates, suppressing residual noise. (4) Pose-Mapping: a geometric retargeting layer transforms shoulder-elbow-wrist triples into the uArm's polar workspace, preserving wrist orientation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21234 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-Time ESFP: Estimating, Smoothing, Filtering, and Pose-Mapping Cui, Qifei Zhou, Yuang Deng, Ruichen Computer Vision and Pattern Recognition Robotics This paper presents ESFP, an end-to-end pipeline that converts monocular RGB video into executable joint trajectories for a low-cost 4-DoF desktop arm. ESFP comprises four sequential modules. (1) Estimating: ROMP lifts each frame to a 24-joint 3-D skeleton. (2) Smoothing: the proposed HPSTM-a sequence-to-sequence Transformer with self-attention-combines long-range temporal context with a differentiable forward-kinematics decoder, enforcing constant bone lengths and anatomical plausibility while jointly predicting joint means and full covariances. (3) Filtering: root-normalized trajectories are variance-weighted according to HPSTM's uncertainty estimates, suppressing residual noise. (4) Pose-Mapping: a geometric retargeting layer transforms shoulder-elbow-wrist triples into the uArm's polar workspace, preserving wrist orientation. |
| title | Real-Time ESFP: Estimating, Smoothing, Filtering, and Pose-Mapping |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2506.21234 |