RealMat: Realistic Materials with Diffusion and Reinforcement Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914015390728192 |
|---|---|
| author | Zhou, Xilong Figueiredo, Pedro Hašan, Miloš Deschaintre, Valentin Guerrero, Paul Hu, Yiwei Kalantari, Nima Khademi |
| author_facet | Zhou, Xilong Figueiredo, Pedro Hašan, Miloš Deschaintre, Valentin Guerrero, Paul Hu, Yiwei Kalantari, Nima Khademi |
| contents | Generative models for high-quality materials are particularly desirable to make 3D content authoring more accessible. However, the majority of material generation methods are trained on synthetic data. Synthetic data provides precise supervision for material maps, which is convenient but also tends to create a significant visual gap with real-world materials. Alternatively, recent work used a small dataset of real flash photographs to guarantee realism, however such data is limited in scale and diversity. To address these limitations, we propose RealMat, a diffusion-based material generator that leverages realistic priors, including a text-to-image model and a dataset of realistic material photos under natural lighting. In RealMat, we first finetune a pretrained Stable Diffusion XL (SDXL) with synthetic material maps arranged in $2 \times 2$ grids. This way, our model inherits some realism of SDXL while learning the data distribution of the synthetic material grids. Still, this creates a realism gap, with some generated materials appearing synthetic. We propose to further finetune our model through reinforcement learning (RL), encouraging the generation of realistic materials. We develop a realism reward function for any material image under natural lighting, by collecting a large-scale dataset of realistic material images. We show that this approach increases generated materials' realism compared to our base model and related work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_01134 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RealMat: Realistic Materials with Diffusion and Reinforcement Learning Zhou, Xilong Figueiredo, Pedro Hašan, Miloš Deschaintre, Valentin Guerrero, Paul Hu, Yiwei Kalantari, Nima Khademi Graphics Computer Vision and Pattern Recognition Generative models for high-quality materials are particularly desirable to make 3D content authoring more accessible. However, the majority of material generation methods are trained on synthetic data. Synthetic data provides precise supervision for material maps, which is convenient but also tends to create a significant visual gap with real-world materials. Alternatively, recent work used a small dataset of real flash photographs to guarantee realism, however such data is limited in scale and diversity. To address these limitations, we propose RealMat, a diffusion-based material generator that leverages realistic priors, including a text-to-image model and a dataset of realistic material photos under natural lighting. In RealMat, we first finetune a pretrained Stable Diffusion XL (SDXL) with synthetic material maps arranged in $2 \times 2$ grids. This way, our model inherits some realism of SDXL while learning the data distribution of the synthetic material grids. Still, this creates a realism gap, with some generated materials appearing synthetic. We propose to further finetune our model through reinforcement learning (RL), encouraging the generation of realistic materials. We develop a realism reward function for any material image under natural lighting, by collecting a large-scale dataset of realistic material images. We show that this approach increases generated materials' realism compared to our base model and related work. |
| title | RealMat: Realistic Materials with Diffusion and Reinforcement Learning |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.01134 |