Philippe Weier

Philippe Weier

I'm currently a PhD student at the University of Saarland. My research focuses on appearance modelling and filtering, differentiable rendering and neural representations.
Before that, I graduated with a Masters in Computer Science at the École Polytechnique Fédérale de Lausanne (EPFL) and worked as a Rendering Researcher at Weta Digital, where I improved the performance of light transport algorithms in the in-house Manuka Renderer.
In my free time, when not programming some toy project, I like to play all sorts of instruments, including the euphonium, the trumpet and the saxophone. You might also see me paint miniatures, climbing walls or cycling :)
Feel free to contact me if you have any questions or simply want to chat.
CV
N-BVH: Neural ray queries with bounding volume hierarchies
Philippe Weier
, Alexander Rath, Élie Michel, Iliyan Georgiev, Philipp Slusallek, Tamy Boubekeur, 2024
ACM SIGGRAPH 2024 (Conference Track)

Abstract
Neural representations have shown spectacular ability to compress complex signals in a fraction of the raw data size. In 3D computer graphics, the bulk of a scene's memory usage is due to polygons and textures, making them ideal candidates for neural compression. Here, the main challenge lies in finding good trade-offs between efficient compression and cheap inference while minimizing training time. In the context of rendering, we adopt a ray-centric approach to this problem and devise N-BVH, a neural compression architecture designed to answer arbitrary ray queries in 3D. Our compact model is learned from the input geometry and substituted for it whenever a ray intersection is queried by a path-tracing engine. While prior neural compression methods have focused on point queries, ours proposes neural ray queries that integrate seamlessly into standard ray-tracing pipelines. At the core of our method, we employ an adaptive BVH-driven probing scheme to optimize the parameters of a multi-resolution hash grid, focusing its neural capacity on the sparse 3D occupancy swept by the original surfaces. As a result, our N-BVH can serve accurate ray queries from a representation that is more than an order of magnitude more compact, providing faithful approximations of visibility, depth, and appearance attributes. The flexibility of our method allows us to combine and overlap neural and non-neural entities within the same 3D scene and extends to appearance level of detail.

Project Page
Neural Prefiltering for Correlation-Aware Levels of Detail
Philippe Weier
, Tobias Zirr, Anton Kaplanyan, Ling-Qi Yan, Philipp Slusallek, 2023
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2023)

Abstract
We introduce a practical general-purpose neural appearance filtering pipeline for physically-based rendering. We tackle the previously difficult challenge of aggregating visibility across many levels of detail from local information only, without relying on learning visibility for the entire scene. The high adaptivity of neural representations allows us to retain geometric correlations along rays and thus avoid light leaks. Common approaches to prefiltering decompose the appearance of a scene into volumetric representations with physically-motivated parameters, where the inflexibility of the fitted models limits rendering accuracy. We avoid assumptions on particular types of geometry or materials, bypassing any special-case decompositions. Instead, we directly learn a compressed representation of the intra-voxel light transport. For such high-dimensional functions, neural networks have proven to be useful representations. To satisfy the opposing constraints of prefiltered appearance and correlation-preserving point-to-point visibility, we use two small independent networks on a sparse multi-level voxel grid. Each network requires 10-20 minutes of training to learn the appearance of an asset across levels of detail. Our method achieves 70-95% compression ratios and around 25% of quality improvements over previous work. We reach interactive to real-time framerates, depending on the level of detail.

Project Page
EARS: Efficiency-Aware Russian Roulette and Splitting
Alexander Rath, Pascal Grittmann, Sebastian Herholz,
Philippe Weier
, Philipp Slusallek, 2022
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2022)

Abstract
Russian roulette and splitting are widely used techniques to increase the efficiency of Monte Carlo estimators. But, despite their popularity, there is little work on how to best apply them. Most existing approaches rely on simple heuristics based on, e.g., surface albedo and roughness. Their efficiency often hinges on user-controlled parameters. We instead iteratively learn optimal Russian roulette and splitting factors during rendering, using a simple and lightweight data structure. Given perfect estimates of variance and cost, our fixed-point iteration provably converges to the optimal Russian roulette and splitting factors that maximize the rendering efficiency. In our application to unidirectional path tracing, we achieve consistent and significant speed-ups over the state of the art.

Project Page
Optimised Path Space Regularisation
Philippe Weier
, Marc Droske, Johannes Hanika, Andrea Weidlich, Jiří Vorba, 2021
Published in Computer Graphics Forum (Proceedings of Eurographics Symposium on Rendering)

Abstract
We present Optimised Path Space Regularisation (OPSR), a novel regularisation technique for forward path tracing algorithms. Our regularisation controls the amount of roughness added to materials depending on the type of sampled paths and trades a small error in the estimator for a drastic reduction of variance in difficult paths, including indirectly visible caustics. We formulate the problem as a joint bias-variance minimisation problem and use differentiable rendering to optimise our model. The learnt parameters generalise to a large variety of scenes irrespective of their geometric complexity. The regularisation added to the underlying light transport algorithm naturally allows us to handle the problem of near-specular and glossy path chains robustly. Our method consistently improves the convergence of path tracing estimators, including state-of-the-art path guiding techniques where it enables finding otherwise hard-to-sample paths and thus, in turn, can significantly speed up the learning of guiding distributions.

Project Page
Rendering Layered Materials with Anisotropic Interfaces
Philippe Weier
and Laurent Belcour, 2020
Published in Journal of Computer Graphics Techniques (JCGT)

Abstract
We present a lightweight and efficient method to render layered materials with anisotropic interfaces. Our work extends the statistical framework of Belcour [2018] to handle anisotropic microfacet models. A key insight to our work is that when projected on the tangent plane, BRDF lobes from an anisotropic GGX distribution are well approximated by ellipsoidal distributions aligned with the tangent frame: its covariance matrix is diagonal in this space. We leverage this property and perform the adding-doubling algorithm on each anisotropy axis independently. We further update the mapping of roughness to directional variance and the evaluation of the average reflectance to account for anisotropy. We extensively tested this model against ground truth.

Project Page
© 2023 Philippe Weier