Related papers: GA-Net: Guided Aggregation Net for End-to-end Ster…

We present a novel architecture for dense correspondence. The current state-of-the-art are Transformer-based approaches that focus on either feature descriptors or cost volume aggregation. However, they generally aggregate one or the other…

This paper introduces a concept of layer aggregation to describe how information from previous layers can be reused to better extract features at the current layer. While DenseNet is a typical example of the layer aggregation mechanism, its…

Near-future large galaxy surveys will encounter blended galaxy images at a fraction of up to 50% in the densest regions of the universe. Current deblending techniques may segment the foreground galaxy while leaving missing pixel intensities…

In real-life applications, certain images utilized are corrupted in which the image pixels are damaged or missing, which increases the complexity of computer vision tasks. In this paper, a deep learning architecture is proposed to deal with…

Broad searches for continuous gravitational wave signals rely on hierarchies of follow-up stages for candidates above a given significance threshold. An important step to simplify these follow-ups and reduce the computational cost is to…

The rapid progress of generative models such as GANs and diffusion models has led to the widespread proliferation of AI-generated images, raising concerns about misinformation, privacy violations, and trust erosion in digital media.…

This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs). Unlike existing methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into…

Topological learning is a wide research area aiming at uncovering the mutual spatial relationships between the elements of a set. Some of the most common and oldest approaches involve the use of unsupervised competitive neural networks.…

Graph convolutional network (GCN) has been successfully applied to many graph-based applications; however, training a large-scale GCN remains challenging. Current SGD-based algorithms suffer from either a high computational cost that…

Semantic segmentation is a fundamental problem in computer vision and it requires high-resolution feature maps for dense prediction. Current coordinate-guided low-resolution feature interpolation methods, e.g., bilinear interpolation,…

Depth estimation is a challenging task of 3D reconstruction to enhance the accuracy sensing of environment awareness. This work brings a new solution with a set of improvements, which increase the quantitative and qualitative understanding…

Many supervised learning tasks have intrinsic symmetries, such as translational and rotational symmetry in image classifications. These symmetries can be exploited to enhance performance. We formulate the symmetry constraints into a concise…

Graph Neural Networks (GNNs) are a promising deep learning approach for circumventing many real-world problems on graph-structured data. However, these models usually have at least one of four fundamental limitations: over-smoothing,…

Environmental perception systems are crucial for high-precision mapping and autonomous navigation, with LiDAR serving as a core sensor providing accurate 3D point cloud data. Efficiently processing unstructured point clouds while extracting…

Depth completion deals with the problem of recovering dense depth maps from sparse ones, where color images are often used to facilitate this task. Recent approaches mainly focus on image guided learning frameworks to predict dense depth.…

Convolutional Neural Networks (CNNs) have gained a significant attraction in the recent years due to their increasing real-world applications. Their performance is highly dependent to the network structure and the selected optimization…

Several leading methods on public benchmarks for depth-from-stereo rely on memory-demanding 4D cost volumes and computationally intensive 3D convolutions for feature matching. We suggest a new way to process the 4D cost volume where we…

A commonly cited inefficiency of neural network training by back-propagation is the update locking problem: each layer must wait for the signal to propagate through the full network before updating. Several alternatives that can alleviate…

Image inpainting techniques have shown promising improvement with the assistance of generative adversarial networks (GANs) recently. However, most of them often suffered from completed results with unreasonable structure or blurriness. To…

The complementary fusion of light detection and ranging (LiDAR) data and image data is a promising but challenging task for generating high-precision and high-density point clouds. This study proposes an innovative LiDAR-guided stereo…