GeRM: A Generative Rendering Model From Physically Realistic to Photorealistic
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918500530913280 |
|---|---|
| author | Lu, Jiayuan Xie, Rengan Jin, Xuancheng Wu, Zhizhen Ye, Qi Xie, Tian Bao, Hujun Huo, Rui Wang. Yuchi |
| author_facet | Lu, Jiayuan Xie, Rengan Jin, Xuancheng Wu, Zhizhen Ye, Qi Xie, Tian Bao, Hujun Huo, Rui Wang. Yuchi |
| contents | While physically-based rendering (PBR) simulates light transport that guarantees physical realism, achieving true photorealistic rendering (PRR) demands prohibitive time and labor, and still struggles to capture the intractable richness of the real world. We propose GeRM, the first multimodal generative rendering model to bridge the gap from PBR to PRR (P2P). We formulate this P2P transition by learning a distribution transfer vector (DTV) field to direct the generative process. To achieve this, we introduce a multi-condition ControlNet that synthesizes PBR images and progressively transitions them into PRR images, guided by G-buffers, text prompts, and cues for enhanced regions. To improve the model's grasp of the image distribution shift driven by text prompts, we propose a residual perceptual transfer mechanism to associate text prompts with corresponding targeted modification regions, which more clearly defines the incremental component updates. To supervise this transfer process, we introduce a multi-agent visual language model framework to construct an expert-guided pairwise transfer dataset, named P2P-50K, where each paired sample corresponds to a specific transfer vector in the DTV field. Extensive experiments demonstrate that GeRM synthesizes high-quality controllable images and outperforms state-of-the-art baselines across diverse applications, including PBR and PRR image synthesis and editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09304 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GeRM: A Generative Rendering Model From Physically Realistic to Photorealistic Lu, Jiayuan Xie, Rengan Jin, Xuancheng Wu, Zhizhen Ye, Qi Xie, Tian Bao, Hujun Huo, Rui Wang. Yuchi Computer Vision and Pattern Recognition While physically-based rendering (PBR) simulates light transport that guarantees physical realism, achieving true photorealistic rendering (PRR) demands prohibitive time and labor, and still struggles to capture the intractable richness of the real world. We propose GeRM, the first multimodal generative rendering model to bridge the gap from PBR to PRR (P2P). We formulate this P2P transition by learning a distribution transfer vector (DTV) field to direct the generative process. To achieve this, we introduce a multi-condition ControlNet that synthesizes PBR images and progressively transitions them into PRR images, guided by G-buffers, text prompts, and cues for enhanced regions. To improve the model's grasp of the image distribution shift driven by text prompts, we propose a residual perceptual transfer mechanism to associate text prompts with corresponding targeted modification regions, which more clearly defines the incremental component updates. To supervise this transfer process, we introduce a multi-agent visual language model framework to construct an expert-guided pairwise transfer dataset, named P2P-50K, where each paired sample corresponds to a specific transfer vector in the DTV field. Extensive experiments demonstrate that GeRM synthesizes high-quality controllable images and outperforms state-of-the-art baselines across diverse applications, including PBR and PRR image synthesis and editing. |
| title | GeRM: A Generative Rendering Model From Physically Realistic to Photorealistic |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.09304 |