VLMaterial: Procedural Material Generation with Large Vision-Language 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_ | 1866910833982832640 |
|---|---|
| author | Li, Beichen Wu, Rundi Solar-Lezama, Armando Zheng, Changxi Shi, Liang Bickel, Bernd Matusik, Wojciech |
| author_facet | Li, Beichen Wu, Rundi Solar-Lezama, Armando Zheng, Changxi Shi, Liang Bickel, Bernd Matusik, Wojciech |
| contents | Procedural materials, represented as functional node graphs, are ubiquitous in computer graphics for photorealistic material appearance design. They allow users to perform intuitive and precise editing to achieve desired visual appearances. However, creating a procedural material given an input image requires professional knowledge and significant effort. In this work, we leverage the ability to convert procedural materials into standard Python programs and fine-tune a large pre-trained vision-language model (VLM) to generate such programs from input images. To enable effective fine-tuning, we also contribute an open-source procedural material dataset and propose to perform program-level augmentation by prompting another pre-trained large language model (LLM). Through extensive evaluation, we show that our method outperforms previous methods on both synthetic and real-world examples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_18623 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VLMaterial: Procedural Material Generation with Large Vision-Language Models Li, Beichen Wu, Rundi Solar-Lezama, Armando Zheng, Changxi Shi, Liang Bickel, Bernd Matusik, Wojciech Computer Vision and Pattern Recognition Graphics Procedural materials, represented as functional node graphs, are ubiquitous in computer graphics for photorealistic material appearance design. They allow users to perform intuitive and precise editing to achieve desired visual appearances. However, creating a procedural material given an input image requires professional knowledge and significant effort. In this work, we leverage the ability to convert procedural materials into standard Python programs and fine-tune a large pre-trained vision-language model (VLM) to generate such programs from input images. To enable effective fine-tuning, we also contribute an open-source procedural material dataset and propose to perform program-level augmentation by prompting another pre-trained large language model (LLM). Through extensive evaluation, we show that our method outperforms previous methods on both synthetic and real-world examples. |
| title | VLMaterial: Procedural Material Generation with Large Vision-Language Models |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2501.18623 |