Alexandre Lamure

Real-Time Volumetric Light Transport Inference without a Path Ludwic Leonard, Ruediger Westermann (Technical University of Munich, Germany) arxiv.org/abs/2611.12103 Abstract: We present a real-time method for reconstructing fully integrated pixel radiance in rendered volumetric media under direct and ambient environmental illumination, using compact, low-cost scene features and statistics. Unlike Monte Carlo denoising pipelines for volumetric rendering, which depend on computationally expensive path-traced radiance estimates, our approach directly infers the final light-transport solution from inexpensive primary-ray and environment sample evaluations. We show that these features form a near-sufficient representation of the scene, enabling accurate reconstruction at substantially lower computational cost. Using an attention-augmented image-to-image network, we demonstrate that complete pixel radiance can be inferred directly from these auxiliary features, without requiring the original radiance signal. Operating in image space also provides a more stable computational cost as the camera zooms into or out of the volume, with substantially less dependence on volume density than approaches based on explicit multiple-scattering simulation. We demonstrate real-time performance and high reconstruction accuracy in challenging volumetric cloud scenarios.

Physically Based Rendering in the Latent Space Vuk Radovanovic, Vishesh Gupta, Adrien Gruson, Binh-Son Hua Paper: arxiv.org/abs/2609.21054 Code (MIT? Soon): github.com/trinity-graphics/… 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.

An Elementary Expression for Multiple Scattering in Homogeneous Microflake Media Jonathan Dupuy arxiv.org/abs/2609.20394 Abstract: We derive a novel diffuse-like BRDF based on microfacet theory. Its main novelty lies in the fact that it admits an elementary expression for both evaluation and importance sampling, while accounting exactly for all scattering orders under the Smith shadowing assumption. As such, it is the first to settle the question of whether such a construction was possible. In practice, the BRDF produces Lambertian reflectance at normal incidence and progressively concentrates reflected light around the mirror direction as incidence approaches grazing. We showcase this effect by comparing rendering results against Lambertian and state-of-the-art stochastic microfacet BRDFs.