Related papers: MultiDepth: Single-Image Depth Estimation via Mult…
As a training and analysis strategy for convolutional neural networks (CNNs), we slice images into tiled segments and use, for training and prediction, segments that both satisfy a criterion of information diversity and contain sufficient…
This paper proposes a new residual convolutional neural network (CNN) architecture for single image depth estimation. Compared with existing deep CNN based methods, our method achieves much better results with fewer training examples and…
Monocular depth estimation and defocus estimation are two fundamental tasks in computer vision. Most existing methods treat depth estimation and defocus estimation as two separate tasks, ignoring the strong connection between them. In this…
Road segmentation is a critical task for autonomous driving systems, requiring accurate and robust methods to classify road surfaces from various environmental data. Our work introduces an innovative approach that integrates LiDAR point…
In image-assisted minimally invasive surgeries (MIS), understanding surgical scenes is vital for real-time feedback to surgeons, skill evaluation, and improving outcomes through collaborative human-robot procedures. Within this context, the…
Multi-task learning (MTL) has received considerable attention, and numerous deep learning applications benefit from MTL with multiple objectives. However, constructing multiple related tasks is difficult, and sometimes only a single task is…
The perception of vehicles and pedestrians in urban scenarios is crucial for autonomous driving. This process typically involves complicated data collection, imposes high computational and hardware demands. To address these limitations, we…
Monocular depth estimation is known as an ill-posed task in which objects in a 2D image usually do not contain sufficient information to predict their depth. Thus, it acts differently from other tasks (e.g., classification and segmentation)…
Multiple instance (MI) learning with a convolutional neural network enables end-to-end training in the presence of weak image-level labels. We propose a new method for aggregating predictions from smaller regions of the image into an…
A novel hierarchical Deep Neural Network (DNN) model is presented to address the task of end-to-end driving. The model consists of a master classifier network which determines the driving task required from an input stereo image and directs…
Pre-training techniques play a crucial role in deep learning, enhancing models' performance across a variety of tasks. By initially training on large datasets and subsequently fine-tuning on task-specific data, pre-training provides a solid…
Convolutional Neural Networks (CNNs) have shown to be powerful medical image segmentation models. In this study, we address some of the main unresolved issues regarding these models. Specifically, training of these models on small medical…
The perception system for autonomous driving generally requires to handle multiple diverse sub-tasks. However, current algorithms typically tackle individual sub-tasks separately, which leads to low efficiency when aiming at obtaining…
Single-view depth estimation from omnidirectional images has gained popularity with its wide range of applications such as autonomous driving and scene reconstruction. Although data-driven learning-based methods demonstrate significant…
This paper addresses the problem of single image depth estimation (SIDE), focusing on improving the quality of deep neural network predictions. In a supervised learning scenario, the quality of predictions is intrinsically related to the…
Fully-automatic execution is the ultimate goal for many Computer Vision applications. However, this objective is not always realistic in tasks associated with high failure costs, such as medical applications. For these tasks, semi-automatic…
State-of-the-art self-supervised learning approaches for monocular depth estimation usually suffer from scale ambiguity. They do not generalize well when applied on distance estimation for complex projection models such as in fisheye and…
Depth cues have been proved very useful in various computer vision and robotic tasks. This paper addresses the problem of monocular depth estimation from a single still image. Inspired by the effectiveness of recent works on multi-scale…
Depth estimation attracts widespread attention in the computer vision community. However, it is still quite difficult to recover an accurate depth map using only one RGB image. We observe a phenomenon that existing methods tend to fail in…
Piece-wise 3D planar reconstruction provides holistic scene understanding of man-made environments, especially for indoor scenarios. Most recent approaches focused on improving the segmentation and reconstruction results by introducing…