Special Seminar in Computer Graphics

Brief Description

Seminar for advanced computer graphics has no exact plan, its purpose is to inform about recent methods in computer graphics. Participants of the seminar present interesting methods from literature or their own research.

CURRENT PROGRAMME

3.3.2021 initial meeting
10.3.2021 No meeting
17.3.2021 Asen Atanasov
A Multiscale Microfacet Model Based on Inverse Bin Mapping
Accurately controllable shading detail is a crucial aspect of realistic appearance modelling. Two fundamental building blocks for this are microfacet BRDFs, which describe the statistical behaviour of infinitely small facets, and normal maps, which provide user-controllable spatio-directional surface features. We analyse the filtering of the combined effect of a microfacet BRDF and a normal map. By partitioning the half-vector domain into bins we show that the filtering problem can be reduced to evaluation of an integral histogram (IH), a generalization of a summed-area table (SAT). Integral histograms are known for their large memory requirements, which are usually proportional to the number of bins. To alleviate this, we introduce Inverse Bin Maps, a specialised form of IH with a memory footprint that is practically independent of the number of bins. Based on these, we present a memory-efficient, production-ready approach for filtering of high resolution normal maps with arbitrary Beckmann flake roughness.
24.3.2021 Tobias Rittig
Neural Acceleration of Scattering-Aware Color 3D Printing 

With the wider availability of full-color 3D printers, color-accurate 3D-print preparation has received increased attention. A key
challenge lies in the inherent translucency of commonly used print materials that blurs out details of the color texture. Previous
work tries to compensate for these scattering effects through strategic assignment of colored primary materials to printer voxels.
To date, the highest-quality approach uses iterative optimization that relies on computationally expensive Monte Carlo light
transport simulation to predict the surface appearance from subsurface scattering within a given print material distribution;
that optimization, however, takes in the order of days on a single machine. In our work, we dramatically speed up the process by
replacing the light transport simulation with a data-driven approach. Leveraging a deep neural network to predict the scattering
within a highly heterogeneous medium, our method performs around two orders of magnitude faster than Monte Carlo rendering
while yielding optimization results of similar quality level. The network is based on an established method from atmospheric
cloud rendering, adapted to our domain and extended by a physically motivated weight sharing scheme that substantially reduces
the network size. We analyze its performance in an end-to-end print preparation pipeline and compare quality and runtime to
alternative approaches, and demonstrate its generalization to unseen geometry and material values. This for the first time enables
full heterogenous material optimization for 3D-print preparation within time frames in the order of the actual printing time.

31.3.2021 No meeting today
7.4.2021 start 15:15

 

Filip Jurčák
Material Picker: Material recognition in images using machine learning

One of the important steps in modeling realistic 3D scenes is setting material appearance of the various scene objects. The goal of our ongoing project is to simplify this often tedious task by providing the 3D artist with an intelligent material picker tool. The tool should allow user to ‘pick’ a material from any given input image by simply pointing to an object. A deep neural network will be trained to achieve this nontrivial goal. An extensive set of training data will be provided, where the complex correspondence between the image pixels and the underlying object material will be available. The network should be then able to recover this pixel-material correspondence from new, previously unseen images.

14.4.2021 No meeting today
21.4.2021 TBA
28.4.2021 Alban Fichet
Efficient Material Reflectance Representation and Editing
Computer graphics is a valuable tool used from industrial applications to entertainment; it enables creation of images from virtual scenes. One of the aims of computer graphics is to generate photorealistic scenes; an important part of realism is relying on the accuracy of material models. Hence, the study of material models and reflectance is crucial. Recently, measured materials gained popularity. This works well for uniform materials but spatially varying materials present multiple challenges in acquisition, storage, rendering and editing.In this presentation, we introduce improvements made to efficiently represent acquired reflectance by reducing memory footprint and allowing artists to edit the appearance of measured materials. These two improvements, memory footprint and editing capabilities makes measured materials practical in production scenes.
5.5.2021 Lucia Tódová
Constrained spectral uplifting
Physically-based spectral rendering is becoming increasingly popular in both commercial and academic areas due to its ability to accurately simulate natural phenomena. However, the production of materials defined by their spectral properties is a tedious and expensive process, which makes the utilization of RGB-based assets in spectral renderers a desired feature. To convert RGB values to their spectral representations, a process called spectral uplifting is employed. As the RGB color space is a finite subset of the visible gamut, there exist multiple conversion techniques producing distinct results, which may cause color inconsistencies under various lighting conditions. This thesis proposes a method for constraining the spectral uplifting process. To be specific, pre-defined mappings of RGB values to their spectral representations are preserved and the rest of the RGB gamut is plausibly uplifted. In order to assess its correctness, this technique is then implemented and evaluated in a spectral renderer. The renders uplifted via our method show minimal discrepancies when compared to the original textures.
12.5.2021 Rector’s day
19.5.2021 Thomas Nindel
A Gradient-Based Framework for 3D Print Appearance OptimizationIn full-color inkjet 3D printing, a key problem is determining the material configuration for the millions of voxels that a printed object is made of. The goal is a configuration that minimises the difference between desired target appearance and the result of the printing process. So far, the techniques used to find such a configuration have relied on domain-specific methods or heuristic optimization, which allowed only a limited level of control over the resulting appearance. We propose to use differentiable volume rendering in a continuous material mixture space, which leads to a framework that can be used as a general tool for optimising inkjet 3D printouts. We demonstrate the technical feasibility of this approach, and use it to attain fine control over the fabricated appearance, and high levels of faithfulness to the specified target.
26.5.2021 Alexander Wilkie
A Fitted Radiance and Attenuation Model for Realistic Atmospheres
We present a fitted model of sky dome radiance and attenuation for realistic terrestrial atmospheres. Using scatterer distribution data from atmospheric measurement data, our model considerably improves on the visual realism of existing analytical clear sky models, as well as of interactive methods that are based on approximating atmospheric light transport. We also provide features not found in fitted models so far: radiance patterns for post-sunset conditions, in-scattered radiance and attenuation values for finite viewing distances, an observer altitude resolved model that includes downward-looking viewing directions, as well as polarisation information. We introduce a fully spherical model for in-scattered radiance that replaces the family of hemispherical functions originally introduced by Perez e.a., and which was extended for several subsequent analytical models: our model relies on reference image compression via tensor decomposition instead.
2.6.2021 Martin Mirbauer
SkyGAN
Project report
9.6.2021 Matúš Goliaš
Gradient boosted segmentation of retinal fundus images
Diploma thesis defense rehearsal
23.6.2021 Bohuš Brečka
Efficient light transport simulation of participating media in color 3D printing.
Diploma thesis defense rehearsal

(Excursion ideas: Eli, other VFX houses, Metrology institute, Valeo, CIIRC, VRgineers, liv.tv)