ControlMat: A Controlled Generative Approach to Material Capture
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910579036258304 |
|---|---|
| author | Vecchio, Giuseppe Martin, Rosalie Roullier, Arthur Kaiser, Adrien Rouffet, Romain Deschaintre, Valentin Boubekeur, Tamy |
| author_facet | Vecchio, Giuseppe Martin, Rosalie Roullier, Arthur Kaiser, Adrien Rouffet, Romain Deschaintre, Valentin Boubekeur, Tamy |
| contents | Material reconstruction from a photograph is a key component of 3D content creation democratization. We propose to formulate this ill-posed problem as a controlled synthesis one, leveraging the recent progress in generative deep networks. We present ControlMat, a method which, given a single photograph with uncontrolled illumination as input, conditions a diffusion model to generate plausible, tileable, high-resolution physically-based digital materials. We carefully analyze the behavior of diffusion models for multi-channel outputs, adapt the sampling process to fuse multi-scale information and introduce rolled diffusion to enable both tileability and patched diffusion for high-resolution outputs. Our generative approach further permits exploration of a variety of materials which could correspond to the input image, mitigating the unknown lighting conditions. We show that our approach outperforms recent inference and latent-space-optimization methods, and carefully validate our diffusion process design choices. Supplemental materials and additional details are available at: https://gvecchio.com/controlmat/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_01700 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | ControlMat: A Controlled Generative Approach to Material Capture Vecchio, Giuseppe Martin, Rosalie Roullier, Arthur Kaiser, Adrien Rouffet, Romain Deschaintre, Valentin Boubekeur, Tamy Computer Vision and Pattern Recognition Graphics Material reconstruction from a photograph is a key component of 3D content creation democratization. We propose to formulate this ill-posed problem as a controlled synthesis one, leveraging the recent progress in generative deep networks. We present ControlMat, a method which, given a single photograph with uncontrolled illumination as input, conditions a diffusion model to generate plausible, tileable, high-resolution physically-based digital materials. We carefully analyze the behavior of diffusion models for multi-channel outputs, adapt the sampling process to fuse multi-scale information and introduce rolled diffusion to enable both tileability and patched diffusion for high-resolution outputs. Our generative approach further permits exploration of a variety of materials which could correspond to the input image, mitigating the unknown lighting conditions. We show that our approach outperforms recent inference and latent-space-optimization methods, and carefully validate our diffusion process design choices. Supplemental materials and additional details are available at: https://gvecchio.com/controlmat/. |
| title | ControlMat: A Controlled Generative Approach to Material Capture |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2309.01700 |