Category Archives: Colloquia

CGV Midterm Master Project Presentations

You are cordially invited to attend the midterm master project presentations on Friday, 16 April starting 14:30. The session will be on Zoom (meeting detail available on request).

The session on 16 April features the two speakers listed below and will take about 1.5 hours.

Speaker: Mika Kuijpers

Title: TBD

Abstract: TBD

Speaker: Zehao Jing

Title: Diffusion Mosaic

Abstract: Diffusion Curve is a vector graphics primitive created by diffusing the given colors of defined Bezier curves. Wang tiles that are squares with colored edges and edge colors of neighbor tiles should be the same are used for tiling the plane.  We implement an approach for generating seamless and aperiodic textures based on diffusion curves and Wang Tiles, called the diffusion mosaic

CGV Midterm Master Project Presentations

You are cordially invited to attend the midterm master project presentations on Friday, 19 March starting 14:30. The session will be on Zoom (meeting detail available on request).

The session on 19 March features the three speakers listed below and will take about 1.5 hours.

Speaker 1: Wouter Raateland

Title: Interactive Wildfire Simulation in Mesoscale Plant Ecosystems

Abstract: Every year, more and larger wildfires occur. Simulations are used to study and predict the behavior of wildfires. Existing simulations at mesoscale lack detail. This work builds a detailed wildfire simulation at mesoscale on top of an existing ecosystem simulation. We implemented a fast numerical model for wood pyrolysis, and a GPU accelerated fluid simulation on an adaptive grid. This simulation can be used to study the effect of different plant distributions and soil and weather conditions on the behavior of wildfires.

Speaker 2: Pieter Kools

Title: Physics-based model for point-based sail reconstruction

Abstract: The Sailing Innovation Centre has been doing research into developing more optimal sail shapes for their sailing boats. Using models to simulate sail shapes, predictions can be made on what the shape of the sail is expected to be under certain conditions. An important step in this research is to measure how well the real life sail shape matches the expected sail shape from their model. In this thesis we propose a physics-based method to reconstruct a sail configuration from a known (possibly flexible) sail shape and a set of measured points on a real-life sail. We will also investigate the impact of the amount of points measured and their positions on the reconstruction result.

Speaker 3: Max Lopes Cunha

Title: Reduced Projective Skinning for real-time deformable characters

Abstract: Character skinning is the art and science of expressing the vertex displacements when a character takes a particular pose. Projective Skinning is a method capable of producing dynamic tissue motion and resolve (self-)collisions in real-time, which we can speed up further by formulating the physics simulation in a reduced space. In this work, we investigate how these subspaces can be derived from data and how to use them to add real-time skin deformation to humanoid characters.

CGV Midterm Master Project Presentations

You are cordially invited to attend the midterm master project presentations on Friday, 19 February starting 14:30. The session will be on Zoom (meeting detail available on request).

The session on 19 February features the three speakers listed below and will take about 1.5 hours.

Speaker 1: Nejc Maček

Title: Real-time relighting of human faces with a low-cost setup

Abstract: Relighting – a process defined as changing the appearance of a subject in an image under novel illumination conditions – often requires specialized equipment to produce believable results. We propose a method to capture an abstract relighting model with a low-cost setup using a smartphone camera. This model is used to perform relighting in real-time on a commodity computer.

Speaker 2: Zhoufan Jia

Title: Fast approximation of the inverse reflector problem

Abstract: Suppose we have a target radiance distribution, a light source and a plane for receiving light. How do we design a reflector that can give a similar result as the target radiance distribution? This is a problem of high interest for light designer and related industry, such as lamp manufactures. The inverse reflector problem can be summarized as a high-dimensional global optimization problem. Some existing algorithms are either not fully compatible with parallel acceleration, or with a too narrow application scope (can only deal with the far-field problem). We proposed a method for generating a fast approximation of the reflector’s inverse design, which can also serve as the initial guess for the a finer optimization.

Speaker 3: Matthias Tavasszy

Title: Real-Time Global Illumination using BRSM and Light Cuts

Abstract: Global illumination is light that bounces through an environment multiple times before it ends up at an observer, which is very computationally expensive to simulate. In order to approximate this effect in real time this work combines two previous works,  Bidirectional Reflective Shadow Maps and Light Cuts in order to quickly generate, organize and sample Virtual Light Points for gathering second-bounce illumination at a given location. The program is implemented in Vulkan using RTX ray tracing for occlusion checks.

CGV Colloquium Friday September 18th

We have two midterm master project presentations on Friday, 18 September starting 15:45. The session will be on Zoom.

Presenter: Berend Baas

Title: Latent shape editing

Abstract: In recent years, deep learning on shapes and manifolds has been used to try and perform a variety of tasks, such as classification, deformation transfer and shape matching. This is often done through architectures such as Autoencoders or Generative Adversarial Networks, that try to learn a vector representation of training shapes, which is then used for downstream tasks.

However, current trained representations are generally poorly structured: Their latent space consists of manifolds that are entangled and highly non-linear. This makes it difficult to predict the results of modifications in the latent space on the output of the network. In this work, we investigate the latent space of shape networks, to try and develop techniques to obtain semantic deformations from latent editing operations. We consider two approaches: developing techniques to navigate complex entangles latent spaces, and developing less entangled and more interpretable representations, that can help in providing semantic editing operations.

Presenter: Ruben Vroegindeweij

Title: Depicting motion in a still image by spatio-temporal image fusion

Abstract: TBD

*Zoom meeting details upon request.

CGV Colloquium Friday September 11th

The CGV Colloquium will start online with a talk by Rana Hanocka (Tel Aviv University) on Friday, September 11 starting 16:00. The meeting is scheduled on Zoom, details are listed below.

Rana Hanocka is a 3rd-year PhD student in computer science at Tel Aviv University advised by Daniel Cohen-Or and Raja Giryes. At the intersection of Computer Graphics and Machine Learning, she is working on ways to use deep learning for manipulating, analyzing and understanding 3D shapes.

Title: Deep Learning on Single Shapes


One of the many difficulties in 3D deep learning is a lack of large, clean and labeled datasets. Acquiring and labeling large amounts of 3D data is not only cumbersome, but also requires using fundamental geometry processing pipelines that are not robust to geometry in the wild. Moreover, even high-quality 3D mesh models for similar shapes are extremely inconsistent with respect to triangulation and water-tightness, for example. On the other hand, training neural networks on single images has demonstrated surprisingly superb performance on a variety of different tasks. In this talk, I will present two recent works which propose training deep networks on a single shape. In Point2Mesh [SIGGRAPH 2020], we leverage the inductive bias of convolutional neural networks to learn a self-prior for surface reconstruction. We iteratively deform an initial mesh to “shrink-wrap” the input point cloud, resulting in a watertight mesh reconstruction. The weight-sharing property of CNNs models recurring and correlated structures within a single shape, and inherently removes noise and outliers. In Deep Geometric Texture Synthesis [SIGGRAPH 2020], we train a hierarchical GAN to learn to model the local geometric textures of a single shape. Our network displaces mesh vertices in any direction (i.e., in the normal and tangential direction), enabling synthesis of geometric textures, which cannot be expressed by a simple 2D displacement map.

*Zoom meeting details upon request.

Updates about upcoming education events

Following the instructions from the TU Delft Executive Board, we are suspending all colloquia sessions, including the midterms.

If you already have a presentation scheduled, please wait and it will be rescheduled to a future date as soon as TU Delft is back to its normal routine.

If you must do your midterm in the upcoming weeks due to time constraints, please contact your supervisor.

For more information about the measures and updates, please refer to TU Delft and RIVM.

CG Colloquium Thursday, March 12th

You are cordially invited to attend our CG Colloquium on Thursday, March 12th, 2020, 15:45-17:45h, Lecture Hall D@ta (Building 36)

The program features the following two speakers:

Prerak Mody

Title: 3D Human Pose Estimation Using a Top-view Depth Camera

Abstract: Delirium is a cause of concern within the health industry due to many postsurgery patients succumbing to this mental disease which disturbs their path to a full recovery. To understand and detect the onset of delirium within hospital ICU rooms, a depth camera (Microsoft Kinect) is attached to the ceiling. This depth data preserves privacy but also provides an opportunity to analyze the interactions taking place between the various stakeholders such as patient, hospital staff and visiting family. This project is being done at Philips Research, Eindhoven where my task is to extract the 3D human pose of individuals in the rooms. To this end, I extract the 3D point cloud data and run a supervised learning technique (i.e. 3D Convolutional Neural Network) to extract human pose. Having established a baseline, I am now investigating unsupervised and semi-supervised techniques to reduce the data and data annotation requirements respectively.

Thomas Saulou

Title: Photoshop for dummies : Energy-based image modification for photography composition

Abstract: Cameras have almost reached the limits in terms of hardware and optics, computational methods are now the major way to improve a photograph. However, too few tools are developed to enhance image composition. In this project, we introduce new methods based on photography rules to help photographers to modify the picture’s composition. We present a general approach to image deformation based on the energy, and applications of this approach to the problems of photography composition. Our method is inspired from works found in the prior art. The key advantage of our operator is the content-aware deformation function, which optimizes the location of the pixels modification. The operator has been developed to change lines composition in photographs.

CG Colloquium Thursday, February 27th

You are cordially invited to attend our CG Colloquium on Thursday, February 27th, 2020, 15:45-17:45h, room Kubus (building 26).

Johan van de Koppel, NIOZ

Title: Do self-organized patterns provide a solid basis for building infinite natural landscapes?

Abstract: Natural landscapes, when unaffected by human interference, are often characterized by a bewildering array of repeating natural patterns. Even in landscapes that are as good as flat, as are many dutch ecosystems, regular spatial patterns are found at many scales because of the interactions of organisms with physical forces, a process called spatial self-organization. In this talk, I will discuss how, by combining patterns at multiple spatial scales and including a multitude of processes, we can create visualisations of natural systems that are – in theory – infinite in size, without resorting to noise as the predominant factor creating heterogeneity spatial patterns occurring in the landscape, the ground and in the natural community (i.e. vegetation), we can build CGI representations that are theoretically infinite in scale. I will describe the origin of the patterns, and demonstrate how to build a visualization using patterns at different scales, using intertidal ecosystems as an example.

CG Colloquium Thursday, February 20th

You are cordially invited to attend our CG Colloquium on Thursday, February 20th, 2020, 15:45-17:45h, room Kubus (building 26).

Jim Whitehead

Title: Procedural Generation Using Linear Constraints

Abstract: Procedural content generation problems sometimes involve systems of linear equality and inequality constraints among the elements being generated. Cassowary is a constraint solver designed for solving these types of constraints at interactive speeds. It is widely used in user interface toolkits, and multiple implementations are available. To date, Cassowary has not been used in procedural content generation. This talk presents Cassowary and gives examples of its use in procedural content generation.

CG Colloquium Thursday, February 13th

You are cordially invited to attend our CG Colloquium on Thursday, February 13th, 2020, 15:45-17:45h, room Wit licht (building 26).

The program features the following two speakers:

Priyanka Bhaskar

Title: Narcolepsy – Exploratory Analysis

Abstract: Narcolepsy is a chronic neurological condition that results from the dysregulation of the sleep-wake cycle occurring in an early stage, specifically in adolescence. Although Narcolepsy occurs in an early stage there is a delay in diagnosis due to multiple reasons such as lack of symptom recognition, misdiagnoses as some of the symptoms overlap with other disorders like epilepsy, depression, insomnia to name a few. As a result of delayed diagnosis, the overall quality of life of a patient is affected.
The symptom pentad of narcolepsy includes excessive daytime sleepiness, cataplexy, hypnagogic hallucinations, sleep paralysis and disturbed nocturnal sleep. However, the symptoms related to narcolepsy are not limited to the pentad and cover a broad range covering symptoms not directly related to sleep, like, increase in weight, binge eating, anxiety, agitation. In order to reduce the delay in diagnosis, apart from having and creating an awareness about narcolepsy and it’s symptoms, it is important to look beyond the symptom pentad and understand the occurrences and interrelationships between these symptoms. Hence, this project aims at performing an exploratory analysis by looking into 20 symptoms, to understand symptom occurrences, the associations between symptoms to
name a few.

Joost Wooning

Title: Using Augmented Reality to assist in Medical Interventions

Abstract: Augmented Reality (AR) is an upcoming technique which can be used to display images overlaid on the normal vision of the user, several systems are on the market, in this project a Microsoft HoloLens will be used. A possible use of this technology is during medical interventions, allowing a surgeon to see displayed images inside a patient during surgery. If used as guidance a high accuracy of displayed projections is required to prevent damaging tissue. Previous work uses external tracking systems to enable accurate projections, using these systems is however not always possible, therefore this project will only use the hardware on a HoloLens. Previous research has shown that the spatial tracking of the HoloLens is not accurate, markers will, therefore, be used to track positions. The goal is to display a projection based on a CT image of a patient in the corresponding position inside the patient and report how accurate this projection is.