Sökning: "sparse 3D"

Visar resultat 1 - 5 av 43 uppsatser innehållade orden sparse 3D.

1. 1. Volumetric Rendering of the Inner Coma of a Theoretically Modelled Comet for Comet Interceptor Mission

   Master-uppsats, Luleå tekniska universitet/Rymdteknik

   Författare :Amal Vinod; [2023]
   Nyckelord :Volumetric rendering; rendering; Comet; Coma; Dust Coma; Gas Coma; Blender; Comet Interceptor;

   Sammanfattning : The Comet Interceptor is a joint mission by European Space Agency (ESA) and Japan Aerospace Exploration Agency (JAXA) which seeks to perform a flyby over a Long Period Comet using a multi-element spacecraft. The Comet Interceptor comprises three spacecrafts- A, B1 and B2. LÄS MER

3. 2. Unsupervised Domain Adaptation for 3D Object Detection Using Adversarial Adaptation : Learning Transferable LiDAR Features for a Delivery Robot

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Mattias Hansson; [2023]
   Nyckelord :Unsupervised Domain Adaptation; 3D Object Detection; Mobile Robotics; Adversarial Adaptation; Computer Vision; Oövervakad Domänanpassning; 3D Objektigenkänning; Mobila Robotar; Motspelaranpassning; Datorseende;

   Sammanfattning : 3D object detection is the task of detecting the full 3D pose of objects relative to an autonomous platform. It is an important perception system that can be used to plan actions according to the behavior of other dynamic objects in an environment. LÄS MER

4. 3. Individual Layer Scaling and Redundancy Reduction of Singleshot Multiplane Images for View Synthesis

   Master-uppsats, Lunds universitet/Matematik LTH

   Författare :Max Bergfelt; [2023]
   Nyckelord :MPI; multiplane images; view synthesis; rendering; computer vision; unity; Mathematics and Statistics;

   Sammanfattning : Image-based rendering for view synthesis is a field within computer vision that has seen a growing number of research activity within the past few years, much due to deep learning techniques emerging, allowing researchers to re-format view synthesis as a learning problem. The multiplane image (MPI) is a recently proposed learning-based layered 3D representation, created from one or a few input images for the purpose of rendering novel views. LÄS MER

5. 4. Beyond Traditional Tomography: X-ray Multi-projection Imaging for Additive Manufacturing

   Kandidat-uppsats, Lunds universitet/Synkrotronljusfysik; Lunds universitet/Fysiska institutionen

   Författare :Maria Esther Vilar Alvarez; [2023]
   Nyckelord :X-ray tomography; X-ray multiprojection-imaging; deep learning; additive manufacturing; synchrotron radiation; Physics and Astronomy;

   Sammanfattning : The main aim of this bachelor thesis is to push the limits of 3D X-ray imaging by studying the minimum number of projections required to retrieve high-quality reconstructions for additive manufacturing processes. This project first focuses on understanding how X-ray tomography works, by reconstructing additive manufacturing data already obtained (from PSI, TOMCAT beamline) using two standard reconstruction algorithms, GRIDREC and SIRT. LÄS MER

7. 5. GPS-Free UAV Geo-Localization Using a Reference 3D Database

   Master-uppsats, Linköpings universitet/Institutionen för systemteknik

   Författare :Justus Karlsson; [2022]
   Nyckelord :Deep Learning; Machine Learning; ML; AI; UAV; GPS-Free; CNN; 3D CNN; GCNN; 3D Database; geolocalization; geo-localization; georegistration; Hidden Markov Model; HMM; satellite; satellite database; Batch-Hard; triplet loss; PyTorch Geometric;

   Sammanfattning : The goal of this thesis has been global geolocalization using only visual input and a 3D database for reference. In recent years Convolutional Neural Networks (CNNs) have seen huge success in the task of classifying images. The flattened tensors at the final layers of a CNN can be viewed as vectors describing different input image features. LÄS MER