Related papers: RocNet: Recursive Octree Network for Efficient 3D …

A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects. Albeit recent efforts made by Transformers with the long sequence modeling…

The use of deep unfolding networks in compressive sensing (CS) has seen wide success as they provide both simplicity and interpretability. However, since most deep unfolding networks are iterative, this incurs significant redundancies in…

3D meshes are fundamental data representations for capturing complex geometric shapes in computer vision and graphics applications. While Convolutional Neural Networks (CNNs) have excelled in structured data like images, extending them to…

Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. We argue they can serve as generic representations for modelling images. In particular, by working in scattering space, we achieve…

The safe operation of automated vehicles depends on their ability to perceive the environment comprehensively. However, occlusion, sensor range, and environmental factors limit their perception capabilities. To overcome these limitations,…

3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the…

Recovering high-resolution images from limited sensory data typically leads to a serious ill-posed inverse problem, demanding inversion algorithms that effectively capture the prior information. Learning a good inverse mapping from training…

Most traditional algorithms for compressive sensing image reconstruction suffer from the intensive computation. Recently, deep learning-based reconstruction algorithms have been reported, which dramatically reduce the time complexity than…

Virtual content creation and interaction play an important role in modern 3D applications such as AR and VR. Recovering detailed 3D models from real scenes can significantly expand the scope of its applications and has been studied for…

In this paper, we introduce 3D-GMNet, a deep neural network for 3D object shape reconstruction from a single image. As the name suggests, 3D-GMNet recovers 3D shape as a Gaussian mixture. In contrast to voxels, point clouds, or meshes, a…

The estimation of crowd count in images has a wide range of applications such as video surveillance, traffic monitoring, public safety and urban planning. Recently, the convolutional neural network (CNN) based approaches have been shown to…

Deep neural networks (DNNs) are so over-parametrized that recent research has found them to already contain a subnetwork with high accuracy at their randomly initialized state. Finding these subnetworks is a viable alternative training…

The storage of medical images is one of the challenges in the medical imaging field. There are variable works that use implicit neural representation (INR) to compress volumetric medical images. However, there is room to improve the…

Detecting unseen instances based on multi-view templates is a challenging problem due to its open-world nature. Traditional methodologies, which primarily rely on 2D representations and matching techniques, are often inadequate in handling…

Recent advances in 3D object detection are made by developing the refinement stage for voxel-based Region Proposal Networks (RPN) to better strike the balance between accuracy and efficiency. A popular approach among state-of-the-art…

3D shape models are naturally parameterized using vertices and faces, \ie, composed of polygons forming a surface. However, current 3D learning paradigms for predictive and generative tasks using convolutional neural networks focus on a…

We introduce and analyze a new technique for model reduction for deep neural networks. While large networks are theoretically capable of learning arbitrarily complex models, overfitting and model redundancy negatively affects the prediction…

Concatenation of the deep network representations extracted from different facial patches helps to improve face recognition performance. However, the concatenated facial template increases in size and contains redundant information.…

Deep learning has become an increasingly popular and powerful methodology for modern pattern recognition systems. However, many deep neural networks have millions or billions of parameters, making them untenable for real-world applications…

Residual networks (ResNets) are a deep learning architecture that substantially improved the state of the art performance in certain supervised learning tasks. Since then, they have received continuously growing attention. ResNets have a…