To address the problem of incomplete Multi-view Stereo (MVS) reconstruction, the initial depth and loss function of the depth residual iterative network are investigated, and a new multi-view stereo reconstruction net...
详细信息
Acquiring a substantial amount of high-quality data for industrial image detection poses significant challenges in the field of computer vision. The imbalance between normal and anomalous samples, where normal samples...
详细信息
In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and ...
详细信息
ISBN:
(纸本)9789464593617;9798331519773
In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and quality in reconstructed images, learning inefficiencies due to mode collapse, and data loss during transmission persist. To address these issues, we propose a novel compression model that incorporates a denoising step with diffusion models, significantly enhancing imagereconstruction fidelity by sub-information(e.g., edge and depth) from leveraging latent space. Empirical experiments demonstrate that our model achieves superior or comparable results in terms of image quality and compression efficiency when measured against the existing models. Notably, our model excels in scenarios of partial image loss or excessive noise by introducing an edge estimation network to preserve the integrity of reconstructed images, offering a robust solution to the current limitations of image compression.
Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular appr...
详细信息
ISBN:
(纸本)9798350353013;9798350353006
Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular approaches still struggle to recover fine geometric details such as face, hands or cloth wrinkles. They are also easily prone to depth ambiguities that result in distorted geometries along the camera optical axis. In this paper, we explore the benefits of incorporating depth observations in the reconstruction process by introducing ANIM, a novel method that reconstructs arbitrary 3D human shapes from single-view RGB-D images with an unprecedented level of accuracy. Our model learns geometric details from both multi-resolution pixel-aligned and voxel-aligned features to leverage depth information and enable spatial relationships, mitigating depth ambiguities. We further enhance the quality of the reconstructed shape by introducing a depth-supervision strategy, which improves the accuracy of the signed distance field estimation of points that lie on the re-constructed surface. Experiments demonstrate that ANIM outperforms state-of-the-art works that use RGB, surface normals, point cloud or RGB-D data as input. In addi-tion, we introduce ANIM-Real, a new multi-modal dataset comprising high-quality scans paired with consumer-grade RGB-D camera, and our protocol to fine-tune ANIM, enabling high-quality reconstructionfrom real-world human capture. https://***/ANIM/
With the maturity of computer networks and camera equipment, video data in the Internet is growing exponentially. However, video resource usually exhibits hole-like missing or occlusion, which may affect the visual co...
详细信息
Measurement of the velocity field in thermal-hydraulic experiments is of great importance for phenomena interpretation and code validation. Direct measurement by means of Particle image Velocimetry (PIV) is challengin...
详细信息
ISBN:
(纸本)9783031643613;9783031643620
Measurement of the velocity field in thermal-hydraulic experiments is of great importance for phenomena interpretation and code validation. Direct measurement by means of Particle image Velocimetry (PIV) is challenging in some multiphase's tests where the measurement system would be strongly affected by the phase interaction. A typical example can refer to the test with steam injection into a water pool where the rapid collapse of bubbles and significant temperature gradient makes it impossible to obtain main flow information in a relatively large steam flux. The goal of this work is to investigate the capability of the use of machine learning for the flow reconstruction of the jet induced by steam condensation from sparse temperature measurement with ThermoCouples (TCs). Two frameworks of (i) 'FDD' using pure data-driven modeling and (ii) 'FPINN' combining data-driven and Physics-Informed Neural Networks (PINN) are proposed and investigated. The frameworks are applied to a single-phase turbulent planar jet with data generated by CFD simulations.
A dynamic imagereconstruction method considering the spatiotemporal evolution characteristics of time-varying distribution is proposed for electrical resistance tomography (ERT). The dynamic inversion problem of ERT ...
详细信息
ISBN:
(纸本)9781665453837
A dynamic imagereconstruction method considering the spatiotemporal evolution characteristics of time-varying distribution is proposed for electrical resistance tomography (ERT). The dynamic inversion problem of ERT is constructed by state-space modeling method with state evolution and observation update equations, and is solved by Kalman filter. To accurately describe the state evolution process of time-vary parameters, the latent variable based statistical modeling method is proposed to construct the state evolution equation. The potential characteristics of the state parameters in the dynamic change process are fully explored and characterized from the data with multivariate regression methods. Numerical and experimental results show that the proposed dynamic imagereconstruction method can improve the imaging quality of ERT for time-varying distribution.
This framework outlines a multi-stage methodology for 3D face reconstruction driven by advancements in deep learning. The process involves image preprocessing with deblurring techniques and subsequent feature extracti...
详细信息
How to generate and recognize 3D models efficiently and accurately is a key problem in image recognition. To solve this problem, Cubes Cycle Particle Swarm (CCPS), a new method combining CycleGAN, Marching Cubes (MC) ...
详细信息
Centralized training methods have shown promising results in MR imagereconstruction, but privacy concerns arise when gathering datafrom multiple institutions. Federated learning, a distributed collaborative training...
详细信息
ISBN:
(纸本)9783031474002;9783031474019
Centralized training methods have shown promising results in MR imagereconstruction, but privacy concerns arise when gathering datafrom multiple institutions. Federated learning, a distributed collaborative training scheme, can utilize multi-center data without the need to transfer data between institutions. However, existing federated learning MR imagereconstruction methods rely on manually designed models which have extensive parameters and suffer from performance degradation when facing heterogeneous data distributions. To this end, this paper proposes a novel FederAted neUral archiTecture search approach fOr MR imagereconstruction (FedAutoMRI). The proposed method utilizes differentiable architecture search to automatically find the optimal network architecture. In addition, an exponential moving average method is introduced to improve the robustness of the client model to address the data heterogeneity issue. To the best of our knowledge, this is the first work to use federated neural architecture search for MR imagereconstruction. Experimental results demonstrate that our proposed FedAutoMRI can achieve promising performances while utilizing a lightweight model with only a small number of model parameters compared to the classical federated learning methods.
暂无评论