TerraFusion: Joint Generation of Terrain Geometry and Texture Using Latent Diffusion Models
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_ | 1866912769967652864 |
|---|---|
| author | Higo, Kazuki Kanai, Toshiki Endo, Yuki Kanamori, Yoshihiro |
| author_facet | Higo, Kazuki Kanai, Toshiki Endo, Yuki Kanamori, Yoshihiro |
| contents | 3D terrain models are essential in fields such as video game development and film production. Since surface color often correlates with terrain geometry, capturing this relationship is crucial to achieving realism. However, most existing methods generate either a heightmap or a texture, without sufficiently accounting for the inherent correlation. In this paper, we propose a method that jointly generates terrain heightmaps and textures using a latent diffusion model. First, we train the model in an unsupervised manner to randomly generate paired heightmaps and textures. Then, we perform supervised learning of an external adapter to enable user control via hand-drawn sketches. Experiments show that our approach allows intuitive terrain generation while preserving the correlation between heightmaps and textures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04050 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TerraFusion: Joint Generation of Terrain Geometry and Texture Using Latent Diffusion Models Higo, Kazuki Kanai, Toshiki Endo, Yuki Kanamori, Yoshihiro Graphics Computer Vision and Pattern Recognition 3D terrain models are essential in fields such as video game development and film production. Since surface color often correlates with terrain geometry, capturing this relationship is crucial to achieving realism. However, most existing methods generate either a heightmap or a texture, without sufficiently accounting for the inherent correlation. In this paper, we propose a method that jointly generates terrain heightmaps and textures using a latent diffusion model. First, we train the model in an unsupervised manner to randomly generate paired heightmaps and textures. Then, we perform supervised learning of an external adapter to enable user control via hand-drawn sketches. Experiments show that our approach allows intuitive terrain generation while preserving the correlation between heightmaps and textures. |
| title | TerraFusion: Joint Generation of Terrain Geometry and Texture Using Latent Diffusion Models |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.04050 |