FAUST: Dataset and evaluation for 3D mesh registration (CVPR 2014)
New scanning technologies are increasing the importance of 3D mesh data and the need for algorithms that can reliably align it. Surface registration is important for building full 3D models from partial scans, creating statistical shape models, shape retrieval, and tracking. The problem is particularly challenging for non-rigid and articulated objects like human bodies. While the challenges of real-world data registration are not present in existing synthetic datasets, establishing ground-truth correspondences for real 3D scans is difficult. We address this with a novel mesh registration technique that combines 3D shape and appearance information to produce high-quality alignments. We define a new dataset called FAUST that contains 300 scans of 10 people in a wide range of poses together with an evaluation methodology. To achieve accurate registration, we paint the subjects with high-frequency textures and use an extensive validation process to ensure accurate ground truth. We find that current shape registration methods have trouble with this real-world data. The dataset and evaluation website are available for research purposes at http://faust.is.tue.mpg.de.
Bogo, F., Romero, J., Loper, M. and Black, M.J.,
FAUST: Dataset and evaluation for 3D mesh registration,
In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, Piscataway, NJ, USA. June 2014.
http://files.is.tue.mpg.de/black/papers/FAUST2014.pdf
Видео FAUST: Dataset and evaluation for 3D mesh registration (CVPR 2014) канала Michael Black
Bogo, F., Romero, J., Loper, M. and Black, M.J.,
FAUST: Dataset and evaluation for 3D mesh registration,
In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, Piscataway, NJ, USA. June 2014.
http://files.is.tue.mpg.de/black/papers/FAUST2014.pdf
Видео FAUST: Dataset and evaluation for 3D mesh registration (CVPR 2014) канала Michael Black
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![VAREN: Very Accurate and Realistic Equine Network (CVPR 2024)](https://i.ytimg.com/vi/CxXHxQyr-K8/default.jpg)
![Problems with SMPL and fixing them with STAR](https://i.ytimg.com/vi/djg1WvqcI0M/default.jpg)
![VIBE: Video Inference for human Body pose and shape Estimation](https://i.ytimg.com/vi/XNzgUhxKC38/default.jpg)
![Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences](https://i.ytimg.com/vi/aahF1xGurmM/default.jpg)
![Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs](https://i.ytimg.com/vi/3x9dimY7o-o/default.jpg)
![Estimating body shape under clothing (CVPR 2017)](https://i.ytimg.com/vi/QOFR77-U30g/default.jpg)
![OSSO: Obtaining Skeletal Shape from Outside (CVPR 2022)](https://i.ytimg.com/vi/1wIiPVNDXY0/default.jpg)
![Meta-commerce in the Age of Avatars](https://i.ytimg.com/vi/cfeXq2_tqtw/default.jpg)
![AGORA human pose and shape dataset (CVPR 2021)](https://i.ytimg.com/vi/G1_CTkJfTOo/default.jpg)
![SMPL: Frequently Asked Questions](https://i.ytimg.com/vi/oznqyXPvRgQ/default.jpg)
![SMPL in VR and AR](https://i.ytimg.com/vi/QorQ_uMkOH4/default.jpg)
![Embodied Hands (SIGGRAPH Asia 2017)](https://i.ytimg.com/vi/_1o21xc3TD0/default.jpg)
![SMPLpix: Neural Avatars from 3D Human Models](https://i.ytimg.com/vi/JY9t4xUAouk/default.jpg)
![Lie Bodies: A Manifold Representation of 3D Human Shape](https://i.ytimg.com/vi/8sqbamA3nFs/default.jpg)
![Visual Imitation with SMPL](https://i.ytimg.com/vi/FHUHzu3CYns/default.jpg)
![Incremental Segmentation and Tracking Over Long Image Sequences, ECCV 92](https://i.ytimg.com/vi/3t558lbmbyI/default.jpg)
![GRAB: A Dataset of Whole-Body Human Grasping of Objects (short version)](https://i.ytimg.com/vi/VHN0DBUB4H8/default.jpg)
![From Variational to Deterministic Autoencoders](https://i.ytimg.com/vi/TiIuFt1KvJ4/default.jpg)
![BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information (CVPR 2022)](https://i.ytimg.com/vi/CSPbb1p5Hso/default.jpg)
![Perceiving Systems' Capture Hall Virtual Tour (English)](https://i.ytimg.com/vi/5czer-NHznE/default.jpg)