Start date: 2025 × End date: 2025 × Subject: Computing methodologies → Rendering ×

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Sampling of Anisotropic Spatial Gaussians for Path Guiding
    (The Eurographics Association, 2025) Lelyakin, Sergey; Schüßler, Vincent; Dachsbacher, Carsten; Günther, Tobias; Montazeri, Zahra
    Directional models in path guiding struggle with representing parallax effects or anisotropic features. Our model instead describes the spatial distribution of a target vertex using a 3D Gaussian mixture model. While this dispenses with the need for reprojection and allows to represent anisotropic features easily, its directional probability density is not readily available, since it involves a marginal integral. In this work, we derive an expression for the PDF of our model in solid angle measure that is practical to evaluate. We demonstrate how our model can improve guiding accuracy in various scenes.
  • Thumbnail Image
    Item
    NOVA-3DGS: No-reference Objective VAlidation for 3D Gaussian Splatting
    (The Eurographics Association, 2025) Piras, Valentina; Bonatti, Amedeo Franco; Maria, Carmelo De; Cignoni, Paolo; Banterle, Francesco; Günther, Tobias; Montazeri, Zahra
    In recent years, radiance field methods, and in particular 3D Gaussian Splatting (3DGS), have distinguished themselves in the field of image-based rendering and scene reconstruction techniques, gaining significant success in academia and being cited in numerous research papers. Like other methods, 3DGS requires a large and diverse dataset of images for network training as a fundamental step to ensure effectiveness and high-quality results. Consequently, the acquisition phase is highly time-consuming, especially considering that a portion of the acquired dataset is not actually used for training but is reserved for testing. This is necessary because all commonly used metrics for evaluating the quality of 3D reconstructions, such as PSNR and SSIM, are reference-based metrics; i.e., requiring a ground truth. In this work, we present NOVA, a study focused on no-reference evaluation of 3DGS renders, based on key metrics in this field: PSNR and SSIM.