Essays about: "geometric network"

Showing result 1 - 5 of 45 essays containing the words geometric network.

  1. 1. Optimizing Realistic 3D Facial Models for VR Avatars through Mesh Simplification

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Beiqian Liu; [2023]
    Keywords : Mesh Simplification; Virtual Reality; Realistic Avatars; 3D Face Reconstruction;

    Abstract : The use of realistic 3D avatars in Virtual Reality (VR) has gained significant traction in applications such as telecommunication and gaming, offering immersive experiences and face-to-face interactions. However, standalone VR devices often face limitations in computational resources and real-time rendering requirements, necessitating the optimization of 3D models through mesh simplification to enhance performance and ensure a smooth user experience. READ MORE

  3. 2. Automatic Detection of Structural Deformations in Batteries from Imaging data using Machine Learning : Exploring the potential of different approaches for efficient structural deformation detection

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Maira Khan; [2023]
    Keywords : CT scan; electrode peaks; jelly roll; keypoints; structural deformation; traditional computer vision; deep neural network; CT-skanning; elektrodtoppar; gelérulle; nyckelpunkter; strukturell deformation; Traditionellt datorseende; djupt neuralt nätverk;

    Abstract : The increasing occurrence of structural deformations in the electrodes of the jelly roll has raised quality concerns during battery manufacturing, emphasizing the need to detect them automatically with the advanced techniques. This thesis aims to explore and provide two models based on traditional computer vision (CV) and deep neural network (DNN) techniques using computed tomography (CT) scan images of jelly rolls to ensure that the product is of high quality. READ MORE

  4. 3. Through the Blur with Deep Learning : A Comparative Study Assessing Robustness in Visual Odometry Techniques

    University essay from Uppsala universitet/Avdelningen för systemteknik

    Author : Alexander Berglund; [2023]
    Keywords : artificial intelligence; AI; machine learning; ML; deep learning; DL; computer vision; neural networks; NN; convolutional neural networks; CNN; visual odometry; VO; robustness; motion blur; AirForestry; localization; navigation; ego-motion; pose estimation; SLAM; DF-VO; DytanVO; ORB-SLAM3; artificiell intelligens; maskininlärning; datorseende;

    Abstract : In this thesis, the robustness of deep learning techniques in the field of visual odometry is investigated, with a specific focus on the impact of motion blur. A comparative study is conducted, evaluating the performance of state-of-the-art deep convolutional neural network methods, namely DF-VO and DytanVO, against ORB-SLAM3, a well-established non-deep-learning technique for visual simultaneous localization and mapping. READ MORE

  5. 4. Compact Digital Track Maps: Enhancing Train Traveller Information at the Crossing of Accuracy and Availability : A comparative analysis of algorithms for generating compact representations of railway tracks

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Adam Andersson; [2023]
    Keywords : Train positioning; Digital track map; Digital map generation; Position measurement; Global navigation satellite system; Cartography; Tågpositionering; Digitala spårkartor; Generering av digitala kartor; Positionsmätning; Satellitnavigation; Kartograf;

    Abstract : Trains are constrained to the railway tracks they operate on. This can be leveraged for absolute train positioning, where a train’s position can be mapped onto a digital track map (DTM). Extensive research has been dedicated to enhancing the accuracy of DTMs. READ MORE

  6. 5. Messing With The Gap: On The Modality Gap Phenomenon In Multimodal Contrastive Representation Learning

    University essay from Uppsala universitet/Industriell teknik

    Author : Mohammad Al-Jaff; [2023]
    Keywords : Multimodal machine learning; Representation learning; Self-supervised learning; contrastive learning; computer vision; computational biology; bioinformatics;

    Abstract : In machine learning, a sub-field of computer science, a two-tower architecture model is a specialised type of neural network model that encodes paired data from different modalities (like text and images, sound and video, or proteomics and gene expression profiles) into a shared latent representation space. However, when training these models using a specific contrastive loss function, known as the multimodalinfoNCE loss, seems to often lead to a unique geometric phenomenon known as the modality gap. READ MORE