Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911361587478528 |
|---|---|
| author | Jiang, Zeren Zheng, Chuanxia Laina, Iro Larlus, Diane Vedaldi, Andrea |
| author_facet | Jiang, Zeren Zheng, Chuanxia Laina, Iro Larlus, Diane Vedaldi, Andrea |
| contents | We propose Mesh4D, a feed-forward model for monocular 4D mesh reconstruction. Given a monocular video of a dynamic object, our model reconstructs the object's complete 3D shape and motion, represented as a deformation field. Our key contribution is a compact latent space that encodes the entire animation sequence in a single pass. This latent space is learned by an autoencoder that, during training, is guided by the skeletal structure of the training objects, providing strong priors on plausible deformations. Crucially, skeletal information is not required at inference time. The encoder employs spatio-temporal attention, yielding a more stable representation of the object's overall deformation. Building on this representation, we train a latent diffusion model that, conditioned on the input video and the mesh reconstructed from the first frame, predicts the full animation in one shot. We evaluate Mesh4D on reconstruction and novel view synthesis benchmarks, outperforming prior methods in recovering accurate 3D shape and deformation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05251 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video Jiang, Zeren Zheng, Chuanxia Laina, Iro Larlus, Diane Vedaldi, Andrea Computer Vision and Pattern Recognition We propose Mesh4D, a feed-forward model for monocular 4D mesh reconstruction. Given a monocular video of a dynamic object, our model reconstructs the object's complete 3D shape and motion, represented as a deformation field. Our key contribution is a compact latent space that encodes the entire animation sequence in a single pass. This latent space is learned by an autoencoder that, during training, is guided by the skeletal structure of the training objects, providing strong priors on plausible deformations. Crucially, skeletal information is not required at inference time. The encoder employs spatio-temporal attention, yielding a more stable representation of the object's overall deformation. Building on this representation, we train a latent diffusion model that, conditioned on the input video and the mesh reconstructed from the first frame, predicts the full animation in one shot. We evaluate Mesh4D on reconstruction and novel view synthesis benchmarks, outperforming prior methods in recovering accurate 3D shape and deformation. |
| title | Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.05251 |