Temporal Residual Jacobians For Rig-free Motion Transfer
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_ | 1866916331434016768 |
|---|---|
| author | Muralikrishnan, Sanjeev Dutt, Niladri Shekhar Chaudhuri, Siddhartha Aigerman, Noam Kim, Vladimir Fisher, Matthew Mitra, Niloy J. |
| author_facet | Muralikrishnan, Sanjeev Dutt, Niladri Shekhar Chaudhuri, Siddhartha Aigerman, Noam Kim, Vladimir Fisher, Matthew Mitra, Niloy J. |
| contents | We introduce Temporal Residual Jacobians as a novel representation to enable data-driven motion transfer. Our approach does not assume access to any rigging or intermediate shape keyframes, produces geometrically and temporally consistent motions, and can be used to transfer long motion sequences. Central to our approach are two coupled neural networks that individually predict local geometric and temporal changes that are subsequently integrated, spatially and temporally, to produce the final animated meshes. The two networks are jointly trained, complement each other in producing spatial and temporal signals, and are supervised directly with 3D positional information. During inference, in the absence of keyframes, our method essentially solves a motion extrapolation problem. We test our setup on diverse meshes (synthetic and scanned shapes) to demonstrate its superiority in generating realistic and natural-looking animations on unseen body shapes against SoTA alternatives. Supplemental video and code are available at https://temporaljacobians.github.io/ . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14958 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Temporal Residual Jacobians For Rig-free Motion Transfer Muralikrishnan, Sanjeev Dutt, Niladri Shekhar Chaudhuri, Siddhartha Aigerman, Noam Kim, Vladimir Fisher, Matthew Mitra, Niloy J. Computer Vision and Pattern Recognition Graphics We introduce Temporal Residual Jacobians as a novel representation to enable data-driven motion transfer. Our approach does not assume access to any rigging or intermediate shape keyframes, produces geometrically and temporally consistent motions, and can be used to transfer long motion sequences. Central to our approach are two coupled neural networks that individually predict local geometric and temporal changes that are subsequently integrated, spatially and temporally, to produce the final animated meshes. The two networks are jointly trained, complement each other in producing spatial and temporal signals, and are supervised directly with 3D positional information. During inference, in the absence of keyframes, our method essentially solves a motion extrapolation problem. We test our setup on diverse meshes (synthetic and scanned shapes) to demonstrate its superiority in generating realistic and natural-looking animations on unseen body shapes against SoTA alternatives. Supplemental video and code are available at https://temporaljacobians.github.io/ . |
| title | Temporal Residual Jacobians For Rig-free Motion Transfer |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2407.14958 |