Browsing by Author "Hermosilla, Pedro"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Deep-learning the Latent Space of Light Transport
    (The Eurographics Association and John Wiley & Sons Ltd., 2019) Hermosilla, Pedro; Maisch, Sebastian; Ritschel, Tobias; Ropinski, Timo; Boubekeur, Tamy and Sen, Pradeep
    We suggest a method to directly deep-learn light transport, i. e., the mapping from a 3D geometry-illumination-material configuration to a shaded 2D image. While many previous learning methods have employed 2D convolutional neural networks applied to images, we show for the first time that light transport can be learned directly in 3D. The benefit of 3D over 2D is, that the former can also correctly capture illumination effects related to occluded and/or semi-transparent geometry. To learn 3D light transport, we represent the 3D scene as an unstructured 3D point cloud, which is later, during rendering, projected to the 2D output image. Thus, we suggest a two-stage operator comprising a 3D network that first transforms the point cloud into a latent representation, which is later on projected to the 2D output image using a dedicated 3D-2D network in a second step. We will show that our approach results in improved quality in terms of temporal coherence while retaining most of the computational efficiency of common 2D methods. As a consequence, the proposed two stage-operator serves as a valuable extension to modern deferred shading approaches.
  • Thumbnail Image
    Item
    Enabling Viewpoint Learning through Dynamic Label Generation
    (The Eurographics Association and John Wiley & Sons Ltd., 2021) Schelling, Michael; Hermosilla, Pedro; Vázquez, Pere-Pau; Ropinski, Timo; Mitra, Niloy and Viola, Ivan
    Optimal viewpoint prediction is an essential task in many computer graphics applications. Unfortunately, common viewpoint qualities suffer from two major drawbacks: dependency on clean surface meshes, which are not always available, and the lack of closed-form expressions, which requires a costly search involving rendering. To overcome these limitations we propose to separate viewpoint selection from rendering through an end-to-end learning approach, whereby we reduce the influence of the mesh quality by predicting viewpoints from unstructured point clouds instead of polygonal meshes. While this makes our approach insensitive to the mesh discretization during evaluation, it only becomes possible when resolving label ambiguities that arise in this context. Therefore, we additionally propose to incorporate the label generation into the training procedure, making the label decision adaptive to the current network predictions. We show how our proposed approach allows for learning viewpoint predictions for models from different object categories and for different viewpoint qualities. Additionally, we show that prediction times are reduced from several minutes to a fraction of a second, as compared to state-of-the-art (SOTA) viewpoint quality evaluation. Code and training data is available at https://github.com/schellmi42/viewpoint_learning, which is to our knowledge the biggest viewpoint quality dataset available.
  • Thumbnail Image
    Item
    Improving Perception of Molecular Surface Visualizations by Incorporating Translucency Effects
    (The Eurographics Association, 2018) Hermosilla, Pedro; Maisch, Sebastian; Vázquez, Pere-Pau; Ropinski, Timo; Puig Puig, Anna and Schultz, Thomas and Vilanova, Anna and Hotz, Ingrid and Kozlikova, Barbora and Vázquez, Pere-Pau
    Molecular surfaces are a commonly used representation in the analysis of molecular structures as they provide a compact description of the space occupied by a molecule and its accessibility. However, due to the high abstraction of the atomic data, fine grain features are hard to identify. Moreover, these representations involve a high degree of occlusions, which prevents the identification of internal features and potentially impacts shape perception. In this paper, we present a set of techniques which are inspired by the properties of translucent materials, that have been developed to improve the perception of molecular surfaces: First, we introduce an interactive algorithm to simulate subsurface scattering for molecular surfaces, in order to improve the thickness perception of the molecule. Second, we present a technique to visualize structures just beneath the surface, by still conveying relevant depth information. And lastly, we introduce reflections and refractions into our visualization that improve the shape perception of molecular surfaces. We evaluate the benefits of these methods through crowd-sourced user studies as well as the feedback from several domain experts.
  • Thumbnail Image
    Item
    Real-Time Visualization of 3D Amyloid-Beta Fibrils from 2D Cryo-EM Density Maps
    (The Eurographics Association, 2020) Kniesel, Hannah; Ropinski, Timo; Hermosilla, Pedro; Kozlíková, Barbora and Krone, Michael and Smit, Noeska and Nieselt, Kay and Raidou, Renata Georgia
    Amyloid-beta fibrils are the result of the accumulation of misfolded amyloid precursor proteins along an axis. These fibrils play a crucial role in the development of Alzheimer's disease, and yet its creation and structure are not fully understood. Visualization is often used to understand the structure of such fibrils. Unfortunately, existing algorithms require high memory consumption limiting their applications. In this paper, we introduce a ray marching algorithm that takes advantage of the inherent repetition in these atomic structures, requiring only a 2D density map to represent the fibril. During ray marching, the texture coordinates are transformed based on the position of the sample along the longitudinal axis, simulating the rotation of the fibrils. Our algorithm reduces memory consumption by a large margin and improves GPU cache hits, making it suitable for real-time visualizations. Moreover, we present several shading algorithms for this type of data, such as shadows or ambient occlusion, in order to improve perception. Lastly, we provide a simple yet effective algorithm to communicate the uncertainty introduced during reconstruction. During the evaluation process, we were able to show, that our approach not only outperforms the Standard Volume Rendering method by significantly lower memory consumption and high image quality for low resolution 2D density maps but also in performance.