Bridging Physically Based Rendering and Diffusion Models with Stochastic Differential Equation
This work addresses the need for fine-grained physical control in generative AI for applications in computer graphics and visual effects, representing an incremental advancement by extending existing diffusion models with physical characteristics.
The paper tackled the problem of limited explicit control over physically grounded shading and material properties in diffusion-based image generators by proposing a unified stochastic formulation that bridges Monte Carlo rendering and diffusion models, enabling physically grounded control over diffusion-generated results across tasks like rendering and material editing.
Diffusion-based image generators excel at producing realistic content from text or image conditions, but they offer only limited explicit control over low-level, physically grounded shading and material properties. In contrast, physically based rendering (PBR) offers fine-grained physical control but lacks prompt-driven flexibility. Although these two paradigms originate from distinct communities, both share a common evolution -- from noisy observations to clean images. In this paper, we propose a unified stochastic formulation that bridges Monte Carlo rendering and diffusion-based generative modeling. First, a general stochastic differential equation (SDE) formulation for Monte Carlo integration under the Central Limit Theorem is modeled. Through instantiation via physically based path tracing, we convert it into a physically grounded SDE representation. Moreover, we provide a systematic analysis of how the physical characteristics of path tracing can be extended to existing diffusion models from the perspective of noise variance. Extensive experiments across multiple tasks show that our method can exert physically grounded control over diffusion-generated results, covering tasks such as rendering and material editing.