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 17 of 17 for “"3d semantic segmentation"”.

  1. DATA EFFICIENT 3D INDOOR SCENE UNDERSTANDING

    3D indoor scene understanding endows the AI agents to understand the surrounding environment, which is widely used in robotics, augmented reality and health-care systems, etc. Particularly, we focus on two fundamental tasks: 3D semantic segmentation for point-level and 3D object detection for …

    nus Repository record for DATA EFFICIENT 3D INDOOR SCENE UNDERSTANDING (opens in a new tab) Download file for DATA EFFICIENT 3D INDOOR SCENE UNDERSTANDING (opens in a new tab)

  2. Addressing Data Scarcity with 2D Projection-Based 3D Point Cloud Semantic Segmentation

    Deep learning-based 3D semantic segmentation requires a large volume of training data to achieve robust generalization and prevent overfitting. However, acquiring extensive 3D datasets remains a significant challenge. This study addresses data scarcity in 3D semantic segmentation by leveraging a 2D …

    concordia Download PDF for Addressing Data Scarcity with 2D Projection-Based 3D Point Cloud Semantic Segmentation (opens in a new tab)

  3. TOWARDS LEARNING SCENE SEMANTICS ON 3D POINT CLOUDS

    … two fundamental and challenging tasks, i.e., 3D object detection and 3D semantic segmentation, towards learning scene semantics on 3D point clouds. We utilize deep learning techniques and develop deep models to infer meaningful semantics for 3D data. When developing deep models for these two …

    nus Repository record for TOWARDS LEARNING SCENE SEMANTICS ON 3D POINT CLOUDS (opens in a new tab) Download file for TOWARDS LEARNING SCENE SEMANTICS ON 3D POINT CLOUDS (opens in a new tab)

  4. Effective methodologies for 3D perception in autonomous vehicles

    … innovative and effective methodologies for 3D perception in autonomous vehicles. Specifically, after an extensive analysis of state of the art works, four contributions are proposed. The first one relates to the LiDAR-camera sensor setup, used for capturing a driving scene, so as to enable …

    greece Repository record for Effective methodologies for 3D perception in autonomous vehicles (opens in a new tab)

  5. LiDAR-based 3D Perception from Multi-frame Point Clouds for Autonomous Driving

    3D perception is a critical component of autonomous driving systems, where accurately detecting objects and understanding the surrounding environment is essential for safety. Recent advances in Light Detection and Ranging (LiDAR) technology and deep neural network architectures have enabled …

    waterloo Repository record for LiDAR-based 3D Perception from Multi-frame Point Clouds for Autonomous Driving (opens in a new tab)

  6. 3D scene understanding and change detection with geometric and image priors

    3D scene understanding, i.e., the task of perceiving three-dimensional scenes, is essential to the vast majority of computer vision applications. Indeed, due to the recent advancements in software and hardware that have made 3D representations widely available, efficient and reliable algorithms for …

    greece Repository record for 3D scene understanding and change detection with geometric and image priors (opens in a new tab)

  7. Multimodal Learning for 3D Perception in Autonomous Driving Environments

    3D scene understanding, enabled by camera and lidar sensors, is crucial for autonomous driving 3D tasks like object detection and segmentation. These sensors have complementary strengths, with lidar providing accurate depth data but returning sparse point clouds, while cameras deliver dense, …

    toronto-retro Repository record for Multimodal Learning for 3D Perception in Autonomous Driving Environments (opens in a new tab)

  8. Self-Supervised Learning Method for Semantic Segmentation of LiDAR Point Clouds

    Semantic segmentation has shown a significant success for achieving comprehensive scene understanding in real-time perception and urban modeling. Over the recent years, there have been significant advancements in semantic segmentation for LiDAR point clouds, largely the adopting of deep learning …

    calgary Repository record for Self-Supervised Learning Method for Semantic Segmentation of LiDAR Point Clouds (opens in a new tab)

  9. Learning dense prediction: from correspondence to segmentation

    … a label for each pixel in the image. Given 3D data (point clouds or RGB-D images) as input, dense prediction can also be extended to 3D space and assign each 3D point/location a label. According to the label type, dense prediction can be mainly categorized as depth estimation, motion …

    oxford Repository record for Learning dense prediction: from correspondence to segmentation (opens in a new tab)

  10. Multi-modal Data-efficient Learning for 3D Machine Vision

    The rapid progress of 3D computer vision has enabled a wide range of applications in autonomous driving, robotics, and augmented reality. Despite this growth, training robust 3D perception models remains challenging due to limited labeled data, the complexity of integrating multiple modalities, and …

    clemson Repository record for Multi-modal Data-efficient Learning for 3D Machine Vision (opens in a new tab)

  11. Enhancing Semantic Segmentation of Large-Scale 3D Point Clouds with Deep Learning Techniques for Urban Digital Twin Creation

    … object changes, or as a foundation for automatic 3D modeling of the urban environment… The applications are numerous and potentially growing, especially when considering classified point clouds as digital assets. However, the automatic and precise extraction of maximum semantic information from an …

    liege Repository record for Enhancing Semantic Segmentation of Large-Scale 3D Point Clouds with Deep Learning Techniques for Urban Digital Twin Creation (opens in a new tab) Download PDF for Enhancing Semantic Segmentation of Large-Scale 3D Point Clouds with Deep Learning Techniques for Urban Digital Twin Creation (opens in a new tab)

  12. Improving OOD Detection, Recognition, and Understanding via Multi-Modal Feature Alignment

    … differ from the training distribution due to semantic shift (e.g., novel object categories) or covariate shift (e.g., changes in lighting or sensor noise). Achieving this robustness requires that AI systems progress from detecting OOD data, to recognizing novel categories within OOD data, and …

    waterloo Repository record for Improving OOD Detection, Recognition, and Understanding via Multi-Modal Feature Alignment (opens in a new tab)

  13. Approaching Reality: Integrating Image-based 3D Modelling and Complex Spatial Data in Archaeological Field Recording

    … Geographic Information Systems and proprietary 3D software. Yet, despite technological advances, state-of-the art digital spatial data are almost equally detached from textual archaeological interpretation as they were using conventional tools decades ago. The thesis presents a study of how …

    whiterose Download PDF for Approaching Reality: Integrating Image-based 3D Modelling and Complex Spatial Data in Archaeological Field Recording (opens in a new tab)

  14. Development of semantic mapping methods and their role in robotics

    … as follows. In Chapter 1, the concept of the semantic perception/recognition of the robot exploration environment is presented andan extensive bibliographic review of the works related to this doctoral dissertation is recorded, in order to better interpret our contribution to science. …

    greece Repository record for Development of semantic mapping methods and their role in robotics (opens in a new tab)

  15. BRIDGING INTERPRETABILITY AND PERFORMANCE IN 3D DEEP LEARNING THROUGH GEOMETRIC INDUCTIVE BIASES

    … limitazioni fondamentali nel deep learning 3D, in particolare per applicazioni critiche di sicurezza come l’ispezione delle reti elettriche. Nonostante i progressi significativi nel campo del 3D scene understanding, la maggior parte dei modelli allo stato dell’arte funziona come black boxes, …

    milano Repository record for BRIDGING INTERPRETABILITY AND PERFORMANCE IN 3D DEEP LEARNING THROUGH GEOMETRIC INDUCTIVE BIASES (opens in a new tab)

  16. An Evaluation of the Performance of Lidar Based Semantic Segmentation Algorithms in Structured and Unstructured Environments

    Existing lidar-based semantic segmentation algorithms and datasets focus on autonomous vehicles operating in urban environments. This has greatly improved the safety and reliability of these autonomous vehicles. A new dataset provides similar lidar data, but instead focusing on off-road …

    alabama Repository record for An Evaluation of the Performance of Lidar Based Semantic Segmentation Algorithms in Structured and Unstructured Environments (opens in a new tab)