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 20 of 67 for “"upsampling"”.

  1. Edge-Preserving Image Upsampling and Image Warping

    … physics simulation. In the context of image upsampling, we assign short rest lengths to pixels along edges, thus the gaps between those pixels are closed, and edge sharpness is recovered. Applying pixel migration on the original image plane, we propose a two-stage approach to painterly …

    carleton Repository record for Edge-Preserving Image Upsampling and Image Warping (opens in a new tab)

  2. Upsampling Indoor LiDAR Point Clouds for Object Detection

    … which need high budgets. Therefore, point cloud upsampling is necessary to derive a dense, complete, and uniform point cloud from a noisy, sparse, and non-uniform one. To address this challenge, we proposed a methodology of utilizing point cloud upsam pling methods to enhance the object detection …

    waterloo Repository record for Upsampling Indoor LiDAR Point Clouds for Object Detection (opens in a new tab)

  3. Improving Visual Processing through Feature Descriptor Enhancement and Depth Upsampling

    … of the thesis is concerned with a novel depth upsampling scheme that improves the quality of low-resolution depth maps. It employs a joint local–nonlocal framework guided by an adaptive bandwidth mechanism that dynamically adjusts the influence of neighboring pixels. A distance-based patch …

    concordia Download PDF for Improving Visual Processing through Feature Descriptor Enhancement and Depth Upsampling (opens in a new tab)

  4. Efficient Deep Networks for Image Matting

    … the skipped information and downsampling- upsampling operations, from which we notice the importance of indices kept in the encoder and recovered in the decoder. Based on the observations, we design data- dependant downsampling and upsampling operators conditioned on features from the …

    adelaide Repository record for Efficient Deep Networks for Image Matting (opens in a new tab)

  5. Multi-scale deep-learning approaches for visual coding and processing

    … to perform geometry and optionally attribute upsampling to improve the QoE. In video compression standards, in-loop filters are developed to alleviate compression artifacts. These in-loop filters are hand-crafted and often sub-optimal in performance. Moreover, such in-loop filters are not …

    umkc Repository record for Multi-scale deep-learning approaches for visual coding and processing (opens in a new tab)

  6. Reconstruction of a composite time series output for a multiple-apeture frequency-domain beamformer

    … as the inverse fast Fourier Transform (FFT), upsampling, and spectral merging. The inverse FFT is used to generate an individual time series output for each aperture. Since the apertures have different sample rates and overlapping frequency ranges, the individual aperture time series are …

    ut-knoxville Repository record for Reconstruction of a composite time series output for a multiple-apeture frequency-domain beamformer (opens in a new tab)

  7. Artificial Count Enhancement of Lung Scintigraphic Images Using Deep Learning Techniques

    … This involved a comparative analysis of standard upsampling and downsampling methods, such as linear interpolation, against techniques designed to preserve Poisson counting statistics. These included linear interpolation followed by Poisson resampling for upsampling and sliding window summation …

    ottawa-retro Repository record for Artificial Count Enhancement of Lung Scintigraphic Images Using Deep Learning Techniques (opens in a new tab)

  8. Group Robustness under the Microscope: How Class Imbalance Shapes the Effectiveness of Last-Layer Retraining

    … class-balancing strategies. While subsetting, upsampling, and upweighting are intended to improve robustness, we show that upsampling and upweighting frequently cause catastrophic WGA collapse in imbalanced datasets, whereas subsetting may remove structurally important minority-subgroup …

    gatech Repository record for Group Robustness under the Microscope: How Class Imbalance Shapes the Effectiveness of Last-Layer Retraining (opens in a new tab)

  9. STUDY OF GROUND SETTLEMENT INDUCED BY TUNNELLING AND DATA ENHANCEMENT FOR SETTLEMENT MONITORING USING LIDAR

    … 4 introduces PCL-Autoencoder, a point cloud upsampling network, improving LiDAR-based settlement monitoring with superior accuracy and efficiency. This research advances understanding and practices in ground settlement management, benefiting engineers and contractors. Identified limitations …

    nus Repository record for STUDY OF GROUND SETTLEMENT INDUCED BY TUNNELLING AND DATA ENHANCEMENT FOR SETTLEMENT MONITORING USING LIDAR (opens in a new tab) Download file for STUDY OF GROUND SETTLEMENT INDUCED BY TUNNELLING AND DATA ENHANCEMENT FOR SETTLEMENT MONITORING USING LIDAR (opens in a new tab)

  10. Audio super-resolution with deep neural networks

    … al. by 1.4 dB for 4x and by up to 2.0 dB for 8x upsampling.

    uiuc Repository record for Audio super-resolution with deep neural networks (opens in a new tab)

  11. Towards data-efficient deep learning with meta-learning and symmetries

    … we propose group equivariant subsampling/upsampling layers which tackles the loss of equivariance in conventional subsampling/upsampling layers. These layers can be used to construct end-to-end equivariant models with improved data-efficiency.</p>

    oxford Repository record for Towards data-efficient deep learning with meta-learning and symmetries (opens in a new tab)

  12. Super-Resolution and Scalable Video Coding

    … codec performance. The discrete cosine transform upsampling filter in SHVC is applied to the base layer reconstructed video, there-fore the reference video for the enhancement layer has scaling artifacts and compression artifacts. The VSR model used to perform upsampling can provide a higher …

    tamu Repository record for Super-Resolution and Scalable Video Coding (opens in a new tab)

  13. Physics-Informed Dynamic 3D Reconstruction: From Gaussian Splatting and Rigid-Body Simulation to Inverse Material Estimation

    … simulation. We first evaluate five point cloud upsampling strategies and a depth-guided point lifting method for static 3DGS initialization. On Mip-NeRF360 and Replica, geometry-aware upsampling consistently improves reconstruction quality, with average best-per-scene PSNR gains of 0.26 dB and …

    waterloo Repository record for Physics-Informed Dynamic 3D Reconstruction: From Gaussian Splatting and Rigid-Body Simulation to Inverse Material Estimation (opens in a new tab)

  14. Semantic Segmentation of LiDAR Point Clouds for 3D Mapping of Underground Space

    … first study of the thesis addresses point cloud upsampling, an essential step for creating high-definition maps that preserve fine structural details while ensuring uniform data distribution for downstream tasks. Five deep learning upsampling models including PU-Net, PU-GAN, PU-GCN, …

    waterloo Repository record for Semantic Segmentation of LiDAR Point Clouds for 3D Mapping of Underground Space (opens in a new tab)

  15. An adaptive, multirate method for eliminating intersymbol interference in non-ideal channel.

    … many multi rate filters (dependent of the upsampling/downsampling factor Mc) that can eliminate ISI. As an illustration, two simple adaptive algorithms for computing the zero ISI filters are presented and applied to discrete multitone transmission (DMT) and discrete wavelet multitone …

    ottawa-retro Repository record for An adaptive, multirate method for eliminating intersymbol interference in non-ideal channel. (opens in a new tab)

  16. Applications of Machine Learning for Remote Sensing and Environmental Monitoring

    … neural networks to the reconstruction and upsampling of satellite-based land surface temperature maps. Chapter 6 presents a model employing geospatial techniques and machine learning methods with a combination of ground-based and remote sensing data to produce a daily ultra-high resolution …

    unt Repository record for Applications of Machine Learning for Remote Sensing and Environmental Monitoring (opens in a new tab)

  17. Line Labelling of Polyhedral Scenes: Comparing Performance and Properties of Different Neural Architectures

    … edge categories. Results indicate that gradually upsampling the encoded features and using recurrent algorithms improve segmentation performance. Furthermore, we perform a series of data-driven experiments to investigate how various scene conditions can influence the performance of these neural …

    guelph Repository record for Line Labelling of Polyhedral Scenes: Comparing Performance and Properties of Different Neural Architectures (opens in a new tab)

  18. Evaluation of null subtraction imaging and interpolation techniques for ultrasound B-mode

    … of ultrasound data. Conventional techniques for upsampling and interpolating the data have demonstrated limited success. This study focuses on evaluating one particular super-resolution method, null subtraction imaging, under these conditions while also demonstrating methods to overcome the …

    uiuc Repository record for Evaluation of null subtraction imaging and interpolation techniques for ultrasound B-mode (opens in a new tab)

  19. Regularized Coordinate-based Neural Representation Learning for Optical Tomography

    … implicitly represents a 3D volume, it enables upsampling to any scale, despite only being optimized on discrete measurements. In addition, the disk space required to store the latent representation is much smaller than the traditional method.

    wustl Repository record for Regularized Coordinate-based Neural Representation Learning for Optical Tomography (opens in a new tab)

  20. Predicting Athlete Performance Using Machine Learning Models

    … of imbalance between classes was dealt with by upsampling. The findings confirm that non-linear ensemble and engineered features can be used to translate physiological and training data into useful and proactive information to coordinate and optimize athletes. Keywords: Sports Analytics, Machine …

    rit Repository record for Predicting Athlete Performance Using Machine Learning Models (opens in a new tab)

Page 1 of 4