Physically Based Rendering in the Latent Space
Vuk Radovanovic, Trinity College Dublin
Vishesh Gupta, Trinity College Dublin
Adrien Gruson, École de Technologie Supérieure
Binh-Son Hua, Trinity College Dublin
In Computer Graphics Forum (Proceedings of Pacific Graphics), 2026.
Abstract
Image diffusion models have shown impressive image generation capabilities but are often hard to control, in contrast to classical computer graphics pipelines such as physically based rendering. However, we observe that there is a bridge between light transport phenomena and the distribution of latent space values produced by such models. Thus, we introduce physically based rendering in the feature space learned by the variational autoencoders in generative models, enabling light transport simulation in the latent space. This allows us to leverage physically based rendering techniques to output latent maps for physically guided content generation. We propose modifications to the rendering equation, which, when paired with a differentiable renderer, can yield an optimal set of scene parameters that require only minimal refinement to accurately render into the pretrained latent space. We train our method on a single rendered image, and then demonstrate the generalization of the method to scene geometry changes, lighting changes, and camera view changes.
Downloads
Publication
- Publisher's official version – external link, may require a subscription
- Paper (author's version), PDF – pre-peer reviewed version (arXiv)
Code & Data
Additional
This is the pre-peer reviewed version of the following article: Radovanovic V., Gupta V., Gruson A., Hua B.-S.: Physically Based Rendering in the Latent Space. Computer Graphics Forum (2026), which will be published in final form at https://doi.org/10.1111/cgf.70633. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions.
Cite
Vuk Radovanovic, Vishesh Gupta, Adrien Gruson, and Binh-Son Hua. Physically Based Rendering In The Latent Space, Computer Graphics Forum (Proceedings of Pacific Graphics), 2026.@article{Radovanovic:2026:LatentRendering, title = {Physically Based Rendering in the Latent Space}, author = {Vuk Radovanovic and Vishesh Gupta and Adrien Gruson and Binh-Son Hua}, journal = {Computer Graphics Forum}, year = {2026}, doi = {10.1111/cgf.70633} }Copy to clipboard