Occlusion Resilient 3D Human Pose Estimation
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_ | 1866911778804334592 |
|---|---|
| author | Roy, Soumava Kumar Badanin, Ilia Honari, Sina Fua, Pascal |
| author_facet | Roy, Soumava Kumar Badanin, Ilia Honari, Sina Fua, Pascal |
| contents | Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. Temporal consistency has been extensively used to mitigate their impact but the existing algorithms in the literature do not explicitly model them.
Here, we apply this by representing the deforming body as a spatio-temporal graph. We then introduce a refinement network that performs graph convolutions over this graph to output 3D poses. To ensure robustness to occlusions, we train this network with a set of binary masks that we use to disable some of the edges as in drop-out techniques.
In effect, we simulate the fact that some joints can be hidden for periods of time and train the network to be immune to that. We demonstrate the effectiveness of this approach compared to state-of-the-art techniques that infer poses from single-camera sequences. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11036 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Occlusion Resilient 3D Human Pose Estimation Roy, Soumava Kumar Badanin, Ilia Honari, Sina Fua, Pascal Computer Vision and Pattern Recognition Machine Learning Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. Temporal consistency has been extensively used to mitigate their impact but the existing algorithms in the literature do not explicitly model them. Here, we apply this by representing the deforming body as a spatio-temporal graph. We then introduce a refinement network that performs graph convolutions over this graph to output 3D poses. To ensure robustness to occlusions, we train this network with a set of binary masks that we use to disable some of the edges as in drop-out techniques. In effect, we simulate the fact that some joints can be hidden for periods of time and train the network to be immune to that. We demonstrate the effectiveness of this approach compared to state-of-the-art techniques that infer poses from single-camera sequences. |
| title | Occlusion Resilient 3D Human Pose Estimation |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2402.11036 |