Michael Wimmer

TU Wien | TU Wien · Institute of Computer Graphics and Algorithms

Novel view synthesis has seen major advances in recent years, with 3D Gaussian splatting offering an excellent level of visual quality, fast training and real-time rendering. However, the resources needed for training and rendering inevitably limit the size of the captured scenes that can be represented with good visual quality. We introduce a hier...

LOD construction is typically implemented as a preprocessing step that requires users to wait before they are able to view the results in real time. We propose an incremental LOD generation approach for point clouds that allows us to simultaneously load points from disk, update an octree-based level-of-detail representation, and render the intermed...

Differentiable rendering methods promise the ability to optimize various parameters of 3d scenes to achieve a desired result. However, lighting design has so far received little attention in this field. In this paper, we introduce a method that enables continuous optimization of the arrangement of luminaires in a 3d scene via differentiable light t...

We present Strokes2Surface, an offline geometry reconstruction pipeline that recovers well‐connected curve networks from imprecise 4D sketches to bridge concept design and digital modeling stages in architectural design. The input to our pipeline consists of 3D strokes' polyline vertices and their timestamps as the 4th dimension, along with additio...

3D surface reconstruction from point clouds is a key step in areas such as content creation, archaeology, digital cultural heritage and engineering. Current approaches either try to optimize a non‐data‐driven surface representation to fit the points, or learn a data‐driven prior over the distribution of commonly occurring surfaces and how they corr...

Architectural design and urban planning are complex design tasks. Predicting the thermal impact of design choices at interactive rates enhances the ability of designers to improve energy efficiency and avoid problematic heat islands while maintaining design quality. We show how to use and adapt methods from computer graphics to efficiently simulate...

We present Strokes2Surface, an offline geometry reconstruction pipeline that recovers well‐connected curve networks from imprecise 4D sketches to bridge concept design and digital modeling stages in architectural design. The input to our pipeline consists of 3D strokes' polyline vertices and their timestamps as the 4th dimension, along with additio...

In the context of digitalization in the industry, a variety of technologies has been developed for system integration and enhanced team collaboration in the Architecture, Engineering and Construction (AEC) industry. Multidisciplinary design requirements are characterized by a high degree of complexity. Early design methods often rely on implicit or...

About: We introduce a GPU‐accelerated LOD construction process that creates a hybrid voxel‐point‐based variation of the widely used layered point cloud (LPC) structure for LOD rendering and streaming. The massive performance improvements provided by the GPU allow us to improve the quality of lower LODs via color filtering while still increasing con...

State-of-the-art workflows within Architecture, Engineering, and Construction (AEC) are still caught in sequential planning processes. Digital design tools in this domain often lack proper communication between different stages of design and relevant domain knowledge. Furthermore, decisions made in the early stages of design, where sketching is use...

About: We introduce a GPU-accelerated LOD construction process that creates a hybrid voxel-point-based variation of the widely used layered point cloud (LPC) structure for LOD rendering and streaming. The massive performance improvements provided by the GPU allow us to improve the quality of lower LODs via color filtering while still increasing con...

Im SFB Advanced Computational Design werden Entwurfswerkzeuge und ‐prozesse durch multi‐ und interdisziplinäre Grundlagenforschung entwickelt. Das Ziel ist, durch eine neue Generation von Computational‐Design‐Methoden höhere Entwurfsqualität und effizientere Prozesse in Architektur und Bauwesen zu ermöglichen. Die Forschung wird in drei Bereichen d...

The accelerated collection of detailed real-world 3D data in the form of ever-larger point clouds is sparking a demand for novel visualization techniques that are capable of rendering billions of point primitives in real-time. We propose a software rasterization pipeline for point clouds that is capable of rendering up to two billion points in real...

Visual error metrics play a fundamental role in the quantification of perceived image similarity. Most recently, use cases for them in real-time applications have emerged, such as content-adaptive shading and shading reuse to increase performance and improve efficiency. A wide range of different metrics has been established, with the most sophistic...

We propose a software rasterization pipeline for point clouds that is capable of brute-force rendering up to two billion points in real time (60fps). Improvements over the state of the art are achieved by batching points in a way that a number of batch-level optimizations can be computed before rasterizing the points within the same rendering pass....

This paper proposes a novel method for deep learning based on the analytical convolution of multidimensional Gaussian mixtures. In contrast to tensors, these do not suffer from the curse of dimensionality and allow for a compact representation, as data is only stored where details exist. Convolution kernels and data are Gaussian mixtures with uncon...

Contemporary applications such as those within Augmented or Virtual Reality (AR/VR) pose challenges for software architectures supporting them, which have to adhere to stringent latency, data transmission, and performance requirements. This manifests in processing 3D models, whose 3D contents are increasingly generated procedurally rather than expl...

Large-scale unstructured point cloud scenes can be quickly visualized without prior reconstruction by utilizing levels-of-detail structures to load an appropriate subset from out-of-core storage for rendering the current view. However, as soon as we need structures within the point cloud, e.g., for interactions between objects, the construction of...

In this paper, we present several compute‐based point cloud rendering approaches that outperform the hardware pipeline by up to an order of magnitude and achieve significantly better frame times than previous compute‐based methods. Beyond basic closest‐point rendering, we also introduce a fast, high‐quality variant to reduce aliasing. We present an...

While commodity GPUs provide a continuously growing range of features and sophisticated methods for accelerating compute jobs, many state-of-the-art solutions for point cloud rendering still rely on the provided point primitives (GL_POINTS, POINTLIST, ...) of graphics APIs for image synthesis. In this paper, we present several compute-based point c...

We propose an efficient out‐of‐core octree generation method for arbitrarily large point clouds. It utilizes a hierarchical counting sort to quickly split the point cloud into small chunks, which are then processed in parallel. Levels of detail are generated by subsampling the full data set bottom up using one of multiple exchangeable sampling stra...

For our society to be more inclusive and accessible, the more than 2.2 billion people worldwide with limited vision should be considered more frequently in design decisions, such as architectural planning. To help architects in evaluating their designs and give medical personnel some insight on how patients experience cataracts, we worked with opht...

A key step in any scanning-based asset creation workflow is to convert unordered point clouds to a surface. Classical methods (e.g., Poisson reconstruction) start to degrade in the presence of noisy and partial scans. Hence, deep learning based methods have recently been proposed to produce complete surfaces, even from partial scans. However, such...

[[Full paper: https://www.cg.tuwien.ac.at/research/publications/2020/luidolt-2020-lightperceptionVR/]] The perception of light is inherently different inside a virtual reality (VR) or augmented reality (AR) simulation when compared to the real world. Conventional head-worn displays (HWDs) are not able to display the same high dynamic range of brig...

Nowadays, point clouds are the standard product when capturing reality independent of scale and measurement technique. Especially, Dense Image Matching (DIM) and Laser Scanning (LS) are state of the art capturing methods for a great variety of applications producing detailed point clouds up to billions of points. In-depth analysis of such huge poin...

Creating photorealistic materials for light transport algorithms requires carefully fine‐tuning a set of material properties to achieve a desired artistic effect. This is typically a lengthy process that involves a trained artist with specialized knowledge. In this work, we present a technique that aims to empower novice and intermediate‐level user...

Research in rendering large point clouds traditionally focused on the generation and use of hierarchical acceleration structures that allow systems to load and render the smallest fraction of the data with the largest impact on the output. The generation of these structures is slow and time consuming, however, and therefore ill‐suited for tasks suc...

We present a real-time rendering technique for photometric polygonal lights. Our method uses a numerical integration technique based on a triangulation to calculate noise-free diffuse shading. We include a dynamic point in the triangulation that provides a continuous near-field illumination resembling the shape of the light emitter and its characte...

Figure 1: The progressive rendering of point clouds via reprojection and filling allows us to maintain real-time frame rates by distributing the rendering of large point clouds over multiple frames, without the need to generate acceleration structures in advance. Filling holes with randomized subsets of the full data set leads to higher quality con...

We propose a compute shader based point cloud rasterizer with up to 10 times higher performance than classic point-based rendering with the GL_POINT primitive. In addition to that, our rasterizer offers 5 byte depth-buffer precision with uniform or customizable distribution, and we show that it is possible to implement a high-quality splatting meth...

Probabilistic distribution models like Gaussian mixtures have shown great potential for improving both the quality and speed of several geometric operators. This is largely due to their ability to model large fuzzy data using only a reduced set of atomic distributions, allowing for large compression rates at minimal information loss. We introduce a...

Global Illumination is affected by the slightest change in a 3D scene, requiring a complete reevaluation of the distributed light. In cases where real-time algorithms are not applicable due to high demands on the achievable accuracy, this recomputation from scratch results in artifacts like flickering or noise, disturbing the visual appearance and...

In this work, we propose an interaction-driven approach streamlined to support and improve a wide range of real-time 2D interaction metaphors for arbitrarily large pointclouds based on detected primitive shapes. Rather than performing shape detection as a costly pre-processing step on the entire point cloud at once, a user-controlled interaction de...

Probabilistic distribution models like Gaussian mixtures have shown great potential for improving both the quality and speed of several geometric operators. This is largely due to their ability to model large fuzzy data using only a reduced set of atomic distributions, allowing for large compression rates at minimal information loss. We introduce a...

Vision impairments, such as cataracts, affect the way many people interact with their environment, yet are rarely considered by architects and lighting designers because of a lack of design tools. To address this, we present a method to simulate vision impairments, in particular cataracts, graphically in virtual reality (VR), using eye tracking for...

Vision impairments, such as cataracts, affect the way many people interact with their environment, yet are rarely considered by architects and lighting designers because of a lack of design tools. To address this, we present a method to simulate vision impairments, in particular cataracts, graphically in virtual reality (VR), using eye tracking for...

Real-time rendering of large point clouds requires acceleration structures that reduce the number of points drawn on screen. State-of-the art algorithms group and render points in hierarchically organized chunks with varying extent and density, which results in sudden changes of density from one level of detail to another, as well as noticeable pop...

This work presents a virtual reality simulation for training different attentional abilities in children and adolescents. In an interdisciplinary project between psychology and computer science, we developed four mini-games that are used during therapy sessions to battle different aspects of attentional disorders. First experiments show that the im...

Rendering tens of millions of points in real time usually requires either high-end graphics cards, or the use of spatial acceleration structures. We introduce a method to progressively display as many points as the GPU memory can hold in real time by reprojecting what was visible and randomly adding additional points to uniformly converge towards t...

In workplaces or publicly accessible buildings, escape routes are signposted according to official norms or international standards that specify distances, angles and areas of interest for the positioning of escape-route signs. In homes for the elderly, in which the residents commonly have degraded mobility and suffer from vision impairments caused...

We propose a parameter‐free method to recover manifold connectivity in unstructured 2D point clouds with high noise in terms of the local feature size. This enables us to capture the features which emerge out of the noise. To achieve this, we extend the reconstruction algorithm hnn‐crust, which connects samples to two (noise‐free) neighbours and ha...

With online repositories for 3D models like 3D Warehouse becoming more prevalent and growing ever larger, new possibilities have emerged for both experienced and inexperienced users. These large collections of shapes can provide inspiration for designers or make it possible to synthesize new shapes by combining different parts from already existing...

Industrial applications like luminaire development (the creation of a luminaire in terms of geometry and material) or lighting design (the efficient and aesthetic placement of luminaires in a virtual scene) rely heavily on high realism and physically correct simulations. Using typical approaches like CAD modeling and offline rendering, this require...

Finding similar points in globally or locally similar shapes has been studied extensively through the use of various point descriptors or shape-matching methods. However, little work exists on finding similar points in dissimilar shapes. In this paper, we present the results of a study where users were given two dissimilar two-dimensional shapes an...

In computer graphics, stochastic sampling is frequently used to efficiently approximate complex functions and integrals. The error of approximation can be reduced by distributing samples according to an importance function, but cannot be eliminated completely. To avoid visible artifacts, sample distributions are sought to be random, but spatially u...

Modeling real-world trees is important in many application areas, including computer graphics, botany and forestry. An example of a modeling method is reconstruction from light detection and ranging (LiDAR) scans. In contrast to terrestrial LiDAR systems, airborne LiDAR systems – even current high-resolution systems – capture only very few samples...

We present a novel framework for visualizing routes on mobile devices. Our framework is suitable for helping users explore their environment. First, given a starting point and a maximum route length, the system retrieves nearby points of interest (POIs). Second, we automatically compute an attractive walking path through the environment trying to p...

Capturing urban scenes using photogrammetric methods has become an interesting alternative to laser scanning in the past years. For the reconstruction of CAD-ready 3D models, two main types of interactive approaches have become prevalent: One uses the generated 3D point clouds to reconstruct polygonal surfaces, while the other focuses on 2D interac...

Grass plays an important role in most natural environments. Most interactive applications use image-based techniques to approximate fields of grass due to the high geometrical complexity, leading to visual artifacts. In this paper, we propose a grass-rendering technique that is capable of drawing each blade of grass as geometrical object in real ti...

Traditionally, building floorplans are designed by architects with their usability, functionality, and architectural aesthetics in mind, however, the structural properties of the distribution of load-bearing walls and columns are usually not taken into account at this stage. In this paper we propose a novel approach for the design of architectural...