Sökning: "3d bilder"

Visar resultat 1 - 5 av 257 uppsatser innehållade orden 3d bilder.

1. 1. 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

3. 2. Shape depiction using Local Light Alignment : Evaluating the shape enhancement capabilities of the Local Light Alignment technique at multiple scales

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

   Författare :Edvard Ahlsén; [2023]
   Nyckelord :Shape depiction; Non-photorealistic rendering; Shading; Multiple scales; Formskildring; ickerealistisk rendering; skuggning; skalrymdsmetoder;

   Sammanfattning : Local Light Alignment is a new shading based technique in the field of shape depiction, a field which concerns itself with techniques to represent and enhance the three-dimensional (3D) shape of objects in two-dimensional (2D) visual media. The main idea of Local Light Alignment is to locally adjust the incoming direction of light to create contrast in a way that enhances the perception of shape and surface detail. LÄS MER

4. 3. Förmedla LEGO-bygginstruktioner i en Augmented Reality miljö med hjälp av HoloLens 2

   Kandidat-uppsats, Blekinge Tekniska Högskola/Institutionen för teknik och estetik

   Författare :Cecilia Ek; [2023]
   Nyckelord :Augmented Reality AR ; Head Mounted Display HMD ; HoloLens 2; LEGO; bygginstruktioner; traditionella medier;

   Sammanfattning : I denna artikel undersöks HoloLens 2 som verktyg för att förmedla LEGO-bygginstruktioner genom att använda Augmented Reality (AR). Traditionella instruktionsmetoder såsom text, bilder och video har börjat få konkurrens av AR-tekniken. LÄS MER

5. 4. Deep Learning-based Regularizers for Cone Beam Computed Tomography Reconstruction

   Master-uppsats, KTH/Matematisk statistik

   Författare :Sabina Syed; Josefin Stenberg; [2023]
   Nyckelord :Adversarial Convex Regularization; Computer Vision; Cone Beam Computed Tomography; Convolutional Neural Networks; Deep Learning; Image Reconstruction; Adversarial Convex Regularization; Bildrekonstruktion; Datorseende; Djupinlärning; Faltningsnätverk; Volymtomografi;

   Sammanfattning : Cone Beam Computed Tomography is a technology to visualize the 3D interior anatomy of a patient. It is important for image-guided radiation therapy in cancer treatment. During a scan, iterative methods are often used for the image reconstruction step. LÄS MER

7. 5. Self-learning for 3D segmentation of medical images from single and few-slice annotation

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

   Författare :Côme Lassarat; [2023]
   Nyckelord :Self-supervised Learning; Segmentation; Medical images; Självövervakad inlärning; segmentering; medicinska bilder;

   Sammanfattning : Training deep-learning networks to segment a particular region of interest (ROI) in 3D medical acquisitions (also called volumes) usually requires annotating a lot of data upstream because of the predominant fully supervised nature of the existing stateof-the-art models. To alleviate this annotation burden for medical experts and the associated cost, leveraging self-learning models, whose strength lies in their ability to be trained with unlabeled data, is a natural and straightforward approach. LÄS MER