Sökning: "scene reconstruction"

Visar resultat 1 - 5 av 53 uppsatser innehållade orden scene reconstruction.

1. 1. Using NeRF- and Mesh-Based Methods to Improve Visualisation of Point Clouds

   Master-uppsats, Lunds universitet/Matematik LTH

   Författare :Vilma Ylvén; Oscar Montelin; [2024]
   Nyckelord :Technology and Engineering; Mathematics and Statistics;

   Sammanfattning : In recent years, the field of generating synthetic images from novel view points has seen some major improvements. Most importantly with the publication of Neural Radiance Fields allowing for extremely detailed and accurate 3D novel views. LÄS MER

3. 2. Utilizing Hydra for Real-Time Reconstruction of Environments in Extended Reality

   Master-uppsats, Lunds universitet/Ergonomi och aerosolteknologi

   Författare :Edward Sjöblom; Hannes Rydén Sonesson; [2024]
   Nyckelord :extended reality; usability testing; Technology and Engineering;

   Sammanfattning : This thesis explores the use of Hydra for real-time reconstruction of environments in extended reality (XR). The development of the prototype was performed in an iterative manner. Three iterations were executed, each resulting in a prototype with improvements related to the takeaways from the preceding prototype. LÄS MER

4. 3. Using Neural Radiance Fields and Gaussian Splatting for 3D reconstruction of aircraft inspections

   Master-uppsats, Lunds universitet/Matematik LTH

   Författare :Roos Eline Bottema; [2024]
   Nyckelord :Technology and Engineering;

   Sammanfattning : The rapid evolution of machine learning techniques has revolutionized computer vision, particularly with the introduction of Neural Radiance Fields (NeRF) and the optimization of 3D Gaussians for rendering novel scene views. These methods, such as NeRF and Gaussian Splatting, have demonstrated success in synthetic data scenarios with consistent lighting and well-captured scenes. LÄS MER

5. 4. Assessing the Efficiency of COLMAP, DROID-SLAM, and NeRF-SLAM in 3D Road Scene Reconstruction

   Master-uppsats, Lunds universitet/Matematik LTH

   Författare :Marcus Ascard; Farjam Movahedi; [2023]
   Nyckelord :3D reconstruction; Visual SLAM; Pose evaluation; Point cloud evaluation; Road scenes; Technology and Engineering;

   Sammanfattning : 3D reconstruction is a field in computer vision which has evolved rapidly as a result of the recent advancements in deep learning. As 3D reconstruction pipelines now can run in real-time, this has opened up new possibilities for teams developing Advanced Driver Assistance Systems (ADAS), which rely on the camera system of the vehicle to enhance the safety and driving experience. LÄS MER

7. 5. Scene Reconstruction From 4D Radar Data with GAN and Diffusion : A Hybrid Method Combining GAN and Diffusion for Generating Video Frames from 4D Radar Data

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

   Författare :Alexandr Djadkin; [2023]
   Nyckelord :Deep generative models; Generative adversarial networks; Diffusion models; GAN; DGM; 4D imaging radar; Djupa generativa modeller; Generativa antagonistiska nätverk; Diffusionsmodeller; GAN; DGM; 4D-bildradar;

   Sammanfattning : 4D Imaging Radar is increasingly becoming a critical component in various industries due to beamforming technology and hardware advancements. However, it does not replace visual data in the form of 2D images captured by an RGB camera. LÄS MER