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 inpainting on the training images and use the inpainted images for further training of the 3D model. Due to inconsistencies in the different inpaintings of the images, the 3D inpainting often becomes blurry. With the advent of 3D Gaussian Splatting (3DGS), we identify a new opportunity for 3D inpainting. As 3DGS is more explicit in nature than NeRF, we can manipulate the 3D Gaussians directly rather than relying on image inpainting. Based on that key idea, we propose a method that works similar to the PatchMatch image inpainting algorithm. We first construct a nearest-neighbour field (NNF) by searching for nearest-neighbour patches throughout the scene that look similar to the area we want to inpaint. After constructing the NNF we copy the contents of the nearest-neighbour patches to the inpainting region and blend them together to obtain the inpainting result. In our experiments we found that our method performs well in terms of texture synthesis but struggles with structure synthesis, similar to the original PatchMatch algorithm. In cases where only texture synthesis is required to inpaint the area our method is able to provide good results, although in some cases pre-processing of the scene is necessary, as we found that better quality inputs (e.g. the scene itself, the surface mesh underlying the scene, and precise masks) drastically improve the results of our method. Moreover, some parameters of the algorithm are highly scene-dependent and by tailoring them to the scene we can further enhance the performance of the algorithm. Besides introducing a 3D inpainting method that directly manipulates the scene contents, our work offers valuable new insights into 3DGS editing in general.

The department of Urbanism at the TU Delft, our clients, research the sentiment in different places, times, ages or genders and compare them to each other. This report describes the purpose, design, implementation and accuracy of a web tool created to get insights into the sentiment people have, de- ducted from social media. The aim of our project was to make research easy and extracting innovative insights from social media.

In our tool, we analysed tweets and their location to collect information about the sentiment different people have towards places. The implementation of our tool consisted of five main components: (1) Twitter-Kafka, processing the tweets from the tweet data stream to our database, (2) face recognition, used for determining whether a tweet comes from a person instead of a company or organisation and for age and gender inference, (3) sentiment analysis, using machine learning to determine whether a tweet is neutral, negative or positive, (4) REST API, for the connection between the front-end and the back-end and (5) the user interface, in the form of an interactive dashboard.

At the beginning of the project, we set up a pipeline that checks the code on multiple things. The testing of the back-end is based on a Python unit test suit. For the build to succeed, all tests must pass and the total branch coverage must be at least 80%. We used Flake8 and ESlint in our build to ensure code quality at all times.

All of the above-mentioned components are up and running. The clients are now able to research the sentiments of people towards places.