PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling
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_ | 1866912375413669888 |
|---|---|
| author | Dirik, Alara Wang, Tuanfeng Ceylan, Duygu Zafeiriou, Stefanos Frühstück, Anna |
| author_facet | Dirik, Alara Wang, Tuanfeng Ceylan, Duygu Zafeiriou, Stefanos Frühstück, Anna |
| contents | We present PRISM, a unified framework that enables multiple image generation and editing tasks in a single foundational model. Starting from a pre-trained text-to-image diffusion model, PRISM proposes an effective fine-tuning strategy to produce RGB images along with intrinsic maps (referred to as X layers) simultaneously. Unlike previous approaches, which infer intrinsic properties individually or require separate models for decomposition and conditional generation, PRISM maintains consistency across modalities by generating all intrinsic layers jointly. It supports diverse tasks, including text-to-RGBX generation, RGB-to-X decomposition, and X-to-RGBX conditional generation. Additionally, PRISM enables both global and local image editing through conditioning on selected intrinsic layers and text prompts. Extensive experiments demonstrate the competitive performance of PRISM both for intrinsic image decomposition and conditional image generation while preserving the base model's text-to-image generation capability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14219 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling Dirik, Alara Wang, Tuanfeng Ceylan, Duygu Zafeiriou, Stefanos Frühstück, Anna Graphics Computer Vision and Pattern Recognition We present PRISM, a unified framework that enables multiple image generation and editing tasks in a single foundational model. Starting from a pre-trained text-to-image diffusion model, PRISM proposes an effective fine-tuning strategy to produce RGB images along with intrinsic maps (referred to as X layers) simultaneously. Unlike previous approaches, which infer intrinsic properties individually or require separate models for decomposition and conditional generation, PRISM maintains consistency across modalities by generating all intrinsic layers jointly. It supports diverse tasks, including text-to-RGBX generation, RGB-to-X decomposition, and X-to-RGBX conditional generation. Additionally, PRISM enables both global and local image editing through conditioning on selected intrinsic layers and text prompts. Extensive experiments demonstrate the competitive performance of PRISM both for intrinsic image decomposition and conditional image generation while preserving the base model's text-to-image generation capability. |
| title | PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.14219 |