Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910910144053248 |
|---|---|
| author | Ludwig, Katja Lorenz, Julian Kienzle, Daniel Bui, Tuan Lienhart, Rainer |
| author_facet | Ludwig, Katja Lorenz, Julian Kienzle, Daniel Bui, Tuan Lienhart, Rainer |
| contents | The basic body shape (i.e., the body shape in T-pose) of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly different, thus inconsistent basic body shape for each video frame. Furthermore, we find that SOTA 3D human pose estimation (HPE) models outperform HME models regarding the precision of the estimated 3D keypoint positions. We solve the problem of inconsistent body shapes by leveraging anthropometric measurements like taken by tailors from humans. We create a model called A2B that converts given anthropometric measurements to basic body shape parameters of human mesh models. We obtain superior and consistent human meshes by combining the A2B model results with the keypoints of 3D HPE models using inverse kinematics. We evaluate our approach on challenging datasets like ASPset or fit3D, where we can lower the MPJPE by over 30 mm compared to SOTA HME models. Further, replacing estimates of the body shape parameters from existing HME models with A2B results not only increases the performance of these HME models, but also guarantees consistent body shapes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17671 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes Ludwig, Katja Lorenz, Julian Kienzle, Daniel Bui, Tuan Lienhart, Rainer Computer Vision and Pattern Recognition The basic body shape (i.e., the body shape in T-pose) of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly different, thus inconsistent basic body shape for each video frame. Furthermore, we find that SOTA 3D human pose estimation (HPE) models outperform HME models regarding the precision of the estimated 3D keypoint positions. We solve the problem of inconsistent body shapes by leveraging anthropometric measurements like taken by tailors from humans. We create a model called A2B that converts given anthropometric measurements to basic body shape parameters of human mesh models. We obtain superior and consistent human meshes by combining the A2B model results with the keypoints of 3D HPE models using inverse kinematics. We evaluate our approach on challenging datasets like ASPset or fit3D, where we can lower the MPJPE by over 30 mm compared to SOTA HME models. Further, replacing estimates of the body shape parameters from existing HME models with A2B results not only increases the performance of these HME models, but also guarantees consistent body shapes. |
| title | Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.17671 |