Birth and Death of a Rose
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_ | 1866909639986118656 |
|---|---|
| author | Geng, Chen Zhang, Yunzhi Wu, Shangzhe Wu, Jiajun |
| author_facet | Geng, Chen Zhang, Yunzhi Wu, Shangzhe Wu, Jiajun |
| contents | We study the problem of generating temporal object intrinsics -- temporally evolving sequences of object geometry, reflectance, and texture, such as a blooming rose -- from pre-trained 2D foundation models. Unlike conventional 3D modeling and animation techniques that require extensive manual effort and expertise, we introduce a method that generates such assets with signals distilled from pre-trained 2D diffusion models. To ensure the temporal consistency of object intrinsics, we propose Neural Templates for temporal-state-guided distillation, derived automatically from image features from self-supervised learning. Our method can generate high-quality temporal object intrinsics for several natural phenomena and enable the sampling and controllable rendering of these dynamic objects from any viewpoint, under any environmental lighting conditions, at any time of their lifespan. Project website: https://chen-geng.com/rose4d |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_05278 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Birth and Death of a Rose Geng, Chen Zhang, Yunzhi Wu, Shangzhe Wu, Jiajun Computer Vision and Pattern Recognition Graphics I.2.10 We study the problem of generating temporal object intrinsics -- temporally evolving sequences of object geometry, reflectance, and texture, such as a blooming rose -- from pre-trained 2D foundation models. Unlike conventional 3D modeling and animation techniques that require extensive manual effort and expertise, we introduce a method that generates such assets with signals distilled from pre-trained 2D diffusion models. To ensure the temporal consistency of object intrinsics, we propose Neural Templates for temporal-state-guided distillation, derived automatically from image features from self-supervised learning. Our method can generate high-quality temporal object intrinsics for several natural phenomena and enable the sampling and controllable rendering of these dynamic objects from any viewpoint, under any environmental lighting conditions, at any time of their lifespan. Project website: https://chen-geng.com/rose4d |
| title | Birth and Death of a Rose |
| topic | Computer Vision and Pattern Recognition Graphics I.2.10 |
| url | https://arxiv.org/abs/2412.05278 |