Related papers: Reconstructing the local density field with combin…
When solving a segmentation task, shaped-base methods can be beneficial compared to pixelwise classification due to geometric understanding of the target object as shape, preventing the generation of anatomical implausible predictions in…
Reconstructing a high-resolution 3D model of an object is a challenging task in computer vision. Designing scalable and light-weight architectures is crucial while addressing this problem. Existing point-cloud based reconstruction…
Modeling object dynamics with a neural network is an important problem with numerous applications. Most recent work has been based on graph neural networks. However, physics happens in 3D space, where geometric information potentially plays…
To derive the convergence field from the gravitational shear (gamma) of the background galaxy images, the classical methods require a convolution of the shear to be performed over the entire sky, usually expressed thanks to the Fast Fourier…
We have developed a convolutional neural network (CNN) to reconstruct the shape of irregular rough particles from their interferometric images. The CNN is based on a UNET architecture with residual block modules. The database has been…
In recent years, there has been a significant increase in the utilization of deep learning methods, particularly convolutional neural networks (CNNs), which have emerged as the dominant approach in various domains that involve structured…
We propose unitary group convolutions (UGConvs), a building block for CNNs which compose a group convolution with unitary transforms in feature space to learn a richer set of representations than group convolution alone. UGConvs generalize…
Deep image hashing aims to map input images into simple binary hash codes via deep neural networks and thus enable effective large-scale image retrieval. Recently, hybrid networks that combine convolution and Transformer have achieved…
Deep neural networks have recently achieved state of the art performance thanks to new training algorithms for rapid parameter estimation and new regularization methods to reduce overfitting. However, in practice the network architecture…
Convolutional neural networks show outstanding results in a variety of computer vision tasks. However, a neural network architecture design usually faces a trade-off between model performance and computational/memory complexity. For some…
Point cloud segmentation and classification are some of the primary tasks in 3D computer vision with applications ranging from augmented reality to robotics. However, processing point clouds using deep learning-based algorithms is quite…
As an image sensing instrument, light field images can supply extra angular information compared with monocular images and have facilitated a wide range of measurement applications. Light field image capturing devices usually suffer from…
With joint learning of sampling and recovery, the deep learning-based compressive sensing (DCS) has shown significant improvement in performance and running time reduction. Its reconstructed image, however, losses high-frequency content…
This paper introduces a novel method for reconstructing meshes from sparse point clouds by predicting edge connection. Existing implicit methods usually produce superior smooth and watertight meshes due to the isosurface extraction…
The reconstruction of a discrete surface from a point cloud is a fundamental geometry processing problem that has been studied for decades, with many methods developed. We propose the use of a deep neural network as a geometric prior for…
Extremely efficient convolutional neural network architectures are one of the most important requirements for limited-resource devices (such as embedded and mobile devices). The computing power and memory size are two important constraints…
Deep convolutional neural networks (CNNs) for image denoising have recently attracted increasing research interest. However, plain networks cannot recover fine details for a complex task, such as real noisy images. In this paper, we…
We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual.…
Neural networks are trained by choosing an architecture and training the parameters. The choice of architecture is often by trial and error or with Neural Architecture Search (NAS) methods. While NAS provides some automation, it often…
Traditional weak-lensing mass reconstruction techniques suffer from various artifacts, including noise amplification and the mass-sheet degeneracy. In Hong et al. (2021), we demonstrated that many of these pitfalls of traditional mass…