Browsing by Author "Novák, Jan"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    NeRF-Tex: Neural Reflectance Field Textures
    (The Eurographics Association, 2021) Baatz, Hendrik; Granskog, Jonathan; Papas, Marios; Rousselle, Fabrice; Novák, Jan; Bousseau, Adrien and McGuire, Morgan
    We investigate the use of neural fields for modeling diverse mesoscale structures, such as fur, fabric, and grass. Instead of using classical graphics primitives to model the structure, we propose to employ a versatile volumetric primitive represented by a neural reflectance field (NeRF-Tex), which jointly models the geometry of the material and its response to lighting. The NeRF-Tex primitive can be instantiated over a base mesh to ''texture'' it with the desired meso and microscale appearance. We condition the reflectance field on user-defined parameters that control the appearance. A single NeRF texture thus captures an entire space of reflectance fields rather than one specific structure. This increases the gamut of appearances that can be modeled and provides a solution for combating repetitive texturing artifacts. We also demonstrate that NeRF textures naturally facilitate continuous level-of-detail rendering. Our approach unites the versatility and modeling power of neural networks with the artistic control needed for precise modeling of virtual scenes. While all our training data is currently synthetic, our work provides a recipe that can be further extended to extract complex, hard-to-model appearances from real images.
  • Thumbnail Image
    Item
    Zero-variance Transmittance Estimation
    (The Eurographics Association, 2021) d'Eon, Eugene; Novák, Jan; Bousseau, Adrien and McGuire, Morgan
    We apply zero-variance theory to the Volterra integral formulation of volumetric transmittance.We solve for the guided sampling decisions in this framework that produce zero-variance ratio tracking and next-flight ratio tracking estimators. In both cases, a zero-variance estimate arises by colliding only with the null particles along the interval. For ratio tracking, this is equivalent to residual ratio tracking with a perfect control. The next-flight zero-variance estimator is of the collision type and can only produce zero-variance estimates if the random walk never terminates. In drawing these new connections, we enrich the theory of Monte Carlo transmittance estimation and provide a new rigorous path-stretching interpretation of residual ratio tracking.