Essays about: "Motion Synthesis"

Showing result 1 - 5 of 21 essays containing the words Motion Synthesis.

  1. 1. Exploring Normalizing Flow Modifications for Improved Model Expressivity

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

    Author : Marcel Juschak; [2023]
    Keywords : Normalizing Flows; Motion Synthesis; Invertible Neural Networks; Glow; MoGlow; Maximum Likelihood Estimation; Generative models; normaliserande flöden; rörelsesyntes; inverterbara neurala nätverk; Glow; MoGlow; maximum likelihood-skattning generativa modeller;

    Abstract : Normalizing flows represent a class of generative models that exhibit a number of attractive properties, but do not always achieve state-of-the-art performance when it comes to perceived naturalness of generated samples. To improve the quality of generated samples, this thesis examines methods to enhance the expressivity of discrete-time normalizing flow models and thus their ability to capture different aspects of the data. READ MORE

  3. 2. Hitta ut till Skåneleden : att underlätta för naturovana personer att ta sig ut i naturen med hjälp av en vandringsled

    University essay from SLU/Dept. of Landscape Architecture, Planning and Management (from 130101)

    Author : Ida Holmberg; [2023]
    Keywords : friluftsliv; tillgänglighet; naturovana; Skåneleden; vandring; vandringsanalys; hinder; strategi; kontinuerlig stop motionvandring;

    Abstract : Det här examensarbetet undersökte hur man kan underlätta för ”naturovana” personer (personer som inte ägnar sig åt friluftsliv) att ta sig ut i naturen genom att vandra på Skåneleden. Genom en litteraturstudie undersökte arbetet olika faktorer som kan hindra personer från att delta i friluftsliv. READ MORE

  4. 3. Implementation of Bolt Detection and Visual-Inertial Localization Algorithm for Tightening Tool on SoC FPGA

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

    Author : Muhammad Ihsan Al Hafiz; [2023]
    Keywords : Bolt detection; Visual-Inertial localization; System-on-Chip SoC ; Field-Programmable Gate Array FPGA ; Machine learning; Perspective-n-Points; Error-State Extended Kalman Filter ESEKF ; High-Level Synthesis HLS ; YOLO; Tightening tool; Bultdetektering; visuell-tröghetslokalisering; System-on-Chip SoC ; Field-Programmable Gate Array FPGA ; Machine Learning; Perspective-n-Points; Error-State Extended Kalman Filter ESEKF ; High-Level Synthesis HLS ; YOLO; åtdragningsverktyg;

    Abstract : With the emergence of Industry 4.0, there is a pronounced emphasis on the necessity for enhanced flexibility in assembly processes. In the domain of bolt-tightening, this transition is evident. Tools are now required to navigate a variety of bolts and unpredictable tightening methodologies. READ MORE

  5. 4. The Buen Vivir as a Real Utopia? Analysing the transformative potential of the Ecuadorian socio-political project for the Good Living

    University essay from Lunds universitet/LUCSUS

    Author : Alexandra Gerer; [2022]
    Keywords : Buen Vivir; Real Utopia; Ecuador; transformation; Sustainability Science; Social Sciences;

    Abstract : Motivated by the need for transformative change and more holistic conceptions of wellbeing, this thesis aims to explore the transformative potential of the Buen Vivir. As a synthesis of indigenous and modern principles, it was integrated in the Ecuadorian constitution. READ MORE

  6. 5. A study of transfer learning on data-driven motion synthesis frameworks

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

    Author : Nuo Chen; [2022]
    Keywords : Transfer learning; data-driven motion synthesis; objective-driven motion generation; rig-agnostic encoding; deep learning-based clustering model; procedural animation; Kunskapsöverföring; data-driven rörelsesyntetisering; procedurell animation; mål-driven animation-genereringsmodel; rig-agnostisk-kodning; djupinlärningsbaserad klusteringsmodel;

    Abstract : Various research has shown the potential and robustness of deep learning-based approaches to synthesise novel motions of 3D characters in virtual environments, such as video games and films. The models are trained with the motion data that is bound to the respective character skeleton (rig). READ MORE