# GeRM: A Generative Rendering Model From Physically Realistic to Photorealistic

arXiv: https://arxiv.org/abs/2604.09304 · HTML: https://mlsanity.com/paper/2604.09304/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 54 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Building Normalizing Flows with Stochastic Interpolants](https://mlsanity.com/paper/2209.15571/) (2022)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model](https://mlsanity.com/paper/2212.05034/) (2022)
- [MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond](https://mlsanity.com/paper/2309.16553/) (2023)
- [RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion models](https://mlsanity.com/paper/2405.00666/) (2024)
- [Leaving Reality to Imagination: Robust Classification via Generated Datasets](https://mlsanity.com/paper/2302.02503/) (2023)
- [I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs](https://mlsanity.com/paper/2303.07634/) (2023)
- [IntrinsicEdit: Precise generative image manipulation in intrinsic space](https://mlsanity.com/paper/2505.08889/) (2025)
- [Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement](https://mlsanity.com/paper/2003.12649/) (2020)
- [PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling](https://mlsanity.com/paper/2504.14219/) (2025)
- [Auto Hair Card Extraction for Smooth Hair with Differentiable Rendering](https://mlsanity.com/paper/2505.18805/) (2025)

## Abstract (arXiv)

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.