E. Eisemann
62 records found
1
Optimal Multiple Importance Resampling
Optimal Spatial Reuse for Monte Carlo Light Transport Simulation
Ray tracing has experienced increasing adoption in various spaces of computer graphics. The ReSTIR (Reservoir-based Spatiotemporal Importance Resampling) family of techniques has enabled several orders of magnitude speedups in light transport simulation algorithms which rely on r
...
Physics-Informed Gaussian Splatting
Solving Partial Differential Equations with Gaussians
The prevalence of partial differential equations (PDEs) in modeling physics and the low speeds of numerical solvers demands more efficient solving methods. For this purpose, machine learning based methods have been proposed, but these are typically discrete, difficult to interpre
...
Edge-aware Bilateral Filtering
Reducing across-edge blurring for the bilateral filter
The bilateral filter is a popular filter in image processing and computer vision. This comes from the fact that it is able to blur images while keeping the structure intact. However, the bilateral filter allows for blurring to happen across edges. This can result in halo-like eff
...
On-Mesh Bilateral Filtering
Bridging the Gap Between Texture and Object Space
Traditional bilateral filters, effective in 2D image processing, often fail to account for the 3D structure of meshes, leading to artifacts in texture filtering. This thesis introduces On-Mesh Bilateral Filtering, a novel method that adapts the bilateral filter to work with non-c
...
Predictable blur behaviour for the bilateral filter
Researching a method for linear behaviour between the blurriness and spatial filter size of the bilateral filter
Unlike traditional blur filters, the bilateral filter exhibits non-linear blur behaviour as its kernel size increases. This atypical blur behaviour makes it challenging to find a good σr . This paper investigates the underlying reasons for this behaviour and proposes methods to a
...
This paper introduces the Quadrilateral filter, an advanced extension of the Bilateral and Trilateral filters aimed at addressing limitations in high-gradient regions of images. While the Bilateral filter effectively preserves edges during smoothing, it struggles with intensity v
...
Accelerating hyperbolic t-SNE using the Lorentz Hyperboloid
Exploring a different way to speed up hyperbolic t-SNE
This paper investigates a method for accelerating hyperbolic t-SNE — a popular high-dimensional data visualization technique. In particular, it focuses on building a hyperbolic t-SNE variant that uses a different model of hyperbolic space (called the Lorentz Hyperboloid model) fo
...
Dimensionality reduction is an important task in high-dimensional data visualisation. Among the popular algorithms for achieving this is t-SNE, which aims to preserve local neighbourhoods in the lower-dimensional embeddings. While t-SNE traditionally works in Euclidean space, emb
...
Procedural Tree Generation
How to efficiently predict branching structures from foliage?
The objective of this project is to train a model that transforms a tree with its foliage into only its branch structure. This is achieved by employing machine-learning techniques, specifically Generative Adverserial Networks (GANs). By utilizing the proposed method, a predictive
...
Procedural Tree Generation
Inverse Modelling of 2D Trees using Graph Neural Networks
The most established and widely used methods for analysing tree images for tasks such as geometry analysis, segmentation and classification often rely on pixels. In this paper, the applicability of analyzing tree geometry based on a graph representation rather than a pixel-based
...
Procedural Tree Generation
Compressing 3D tree for faster rendering
Trees are essential components of both real and digital environments. Therefore, it is important to have 3D models of trees that are of high quality and computationally efficient. One way to achieve this is by compressing a high-quality model using billboard rendering, which invo
...
L-Systems allow for the efficient procedeural generation of trees to be used for rendering in video games and simulations. Currently, however, it is difficult to engineer grammars that mimic the behaviours of real life trees in 3 dimensions. To be able to deduce them, the skeleto
...
Image inpainting is a problem that has been well studied over the last decades. In contrast, for 3D reconstructions such as neural radiance fields (NeRFs), work in this area is still limited. Most existing 3D inpainting methods follow a similar approach: they perform image inpain
...
This dissertation develops intrinsic approaches to learning and computing on curved surfaces. Specifically, we work on three tasks: analyzing 3D shapes using convolutional neural networks (CNNs), solving linear systems on curved surfaces, and recovering appearance properties from
...
Animating Still Images
Folding Texture Design and Synthesis
The phenomenon of one element moving and progressively overlaying another is common in nature, such as waves swashing and backwashing, or eyelids moving over eyeballs while blinking. Folding Texture, which was proposed by Thorben, can simulate this texture “folding” visual effect
...
With the current state-of-the-art research, exporting a NeRF to a mesh has the side effect of having to evaluate a Multi Layer Perceptron at render-time, causing a significant decrease in performance. We have found a way to use K-Means clustering to pre-compute values for this ML
...
Simulating lighting is one of the most important parts of rendering 3D scenes. While lighting coming directly from a light source is easy to simulate in real-time, indirect illumination is more difficult. One of the methods used to convincingly approximate indirect illumination i
...
This document describes the work performed the master thesis on a new approach to visualisation for music. We investigate how visualisation of (latent) characteristics of a song can improve user-guided search and exploration. The need for such visualisation is described, followed
...
In this paper, we present a study to improve using neural networks for acoustic reflection localization. Our study focuses on the reimplementation of the proposed neural network model by Bologni et al. and investigates the effect of adding a third microphone to the microphone arr
...