Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 14 of 14 for “"Multi-view geometry"”.
-
Robust 2D and 3D registration with deep neural networks
<p>Recovering 3D geometry is a crucial task in computer vision, essential for accurate world reconstruction and perception. Modern applications in AR, VR, autonomous driving, and medical imaging rely heavily on 3D and 4D reconstruction techniques. This thesis aims to enhance registration methods, …
-
A Low-Cost RGB-Based Multi-Camera Motion Capture System for Metric 3D Tracking of Mobile Robots
… difficulty maintaining metric consistency across multiple viewpoints. This thesis presents a low-cost, multi-camera, marker-based motion capture system using RGB cameras that achieves metrically consistent three-dimensional reconstruction without hardware synchronization. Camera intrinsics are …
-
3D Scene Reconstruction from A Monocular Image
… approaches to address this task are based on multi-view geometry, which create correspondence of feature points with consecutive frames or multiple views. Finally, 3D information of these feature points can be recovered. In contrast, we aim to achieve dense 3D scene shape reconstruction from a …
-
From video to virtual: object-centric 3D scene understanding from videos
… provide natural supervision through motion and viewpoint changes, yet inferring geometry, objectness, and semantics directly from such unconstrained input remains difficult. This thesis develops methods for object-centric 3D scene understanding from video, combining geometric priors, neural …
-
Semantic and Geometry-Aware 3D Reconstruction of Outdoor Scenes Using Low-Cost Vision Sensors
… systems due to geometric degeneracies, limited viewpoint diversity, and forward-dominant motion. While classical multi-view geometry provides a rigorous mathematical foundation for sparse reconstruction, its performance degrades under low-parallax conditions typical of autonomous driving …
-
Advancing Total Body Photography for Early Detection and Spatio-temporal Monitoring of Skin Cancer
… We formulate the TBP scanning problem as a multi-view capture when restricted to determining the camera’s depth of field. Leveraging multi-view geometry in 3D vision, we propose a shape-aware focusing method to optimize the in-focus surface coverage of the subject in a TBP scan. Starting …
-
How Geometry Meets Learning in Pose Estimation
… usually rely on the 3D CAD model and require a multi-step scheme to compute the pose. We alternatively use the idea of direct pose regression for objects based on a region proposed network Mask R-CNN, which is well-known for object detection and instance segmentation. Our newly proposed network …
-
Learning Latent Image Representations with Prior Knowledge
… different problems: (i) How to encode epipolar geometry in deep learning architectures for multi-view stereo. The key of multi-view stereo is to find the matched correspondence across images. In this thesis, a learning-based method inspired by the classical plane sweep algorithm is studied. The …
-
Computer vision-based structural assessment exploiting large volumes of images
Visual assessment is a process to understand the state of a structure based on evaluations originating from visual information. Recent advances in computer vision to explore new sensors, sensing platforms and high-performance computing have shed light on the potential for vision-based visual …
-
Image based automatic vehicle damage detection
… by inter object reflection, we propose to apply multi-view geometry techniques on two photographs of the vehicle taken from different view points. To this end, we also develop a robust method to obtain reliable point correspondences across the photographs which are dominated by large reflective …
-
Computational miniature mesoscope for large-scale 3D fluorescence imaging
… 3D imaging across a wide imaging field-of-view (FOV) of 7~8 mm and an extended depth-of-field (DOF) of 0.8~2.5 mm with a high lateral (7 um) and axial resolution (25 um). The CM2 is a novel fluorescence imaging device that achieves large-scale illumination and single-shot 3D imaging on a …
-
Structured Indoor Reconstruction from Sparse Unposed Panoramas: Coarse Prediction to Generative Geometric Refinement
… difficult due to pose uncertainty, limited cross-view overlap, occlusion, and the inherently global nature of floor-plan structure. This thesis studies learning-based methods for structured indoor reconstruction in this setting, with the goal of recovering precise camera pose, geometry, and …
-
Efficient and Accurate Visual-Inertial Localization and Mapping
… paradigms is to combine VIO and BA in a multi-threaded manner so as to achieve low-latency localization through the VIO, while correcting its drift with the precise map built by the BA. However, to maintain the efficiency of the VIO, approximation is required when combining the data from …
-
Sparse Multi-View Computer Vision for 3D Human and Scene Understanding
… and intelligent interactive systems. Multi-camera systems, by capturing multiple viewpoints simultaneously, enable robust tracking and reconstruction of human poses in 3D, overcoming limitations of single-view approaches. This thesis addresses key bottlenecks encountered when designing …