Related papers: MobileXNet: An Efficient Convolutional Neural Netw…
Autonomous driving is a challenging topic that requires complex solutions in perception tasks such as recognition of road, lanes, traffic signs or lights, vehicles and pedestrians. Through years of research, computer vision has grown…
Distributed deep neural networks (DNNs) have become central to modern computer vision, yet their deployment on resource-constrained edge devices remains hindered by substantial parameter counts, computational demands, and the probability of…
Monocular depth estimation plays a crucial role in 3D recognition and understanding. One key limitation of existing approaches lies in their lack of structural information exploitation, which leads to inaccurate spatial layout,…
Deep neural object detection or segmentation networks are commonly trained with pristine, uncompressed data. However, in practical applications the input images are usually deteriorated by compression that is applied to efficiently transmit…
Depth completion is a crucial task in autonomous driving, aiming to convert a sparse depth map into a dense depth prediction. Due to its potentially rich semantic information, RGB image is commonly fused to enhance the completion effect.…
Deep Convolutional Neural Networks (CNNs) are capable of learning unprecedentedly effective features from images. Some researchers have struggled to enhance the parameters' efficiency using grouped convolution. However, the relation between…
Although cameras are ubiquitous, robotic platforms typically rely on active sensors like LiDAR for direct 3D perception. In this work, we propose a novel self-supervised monocular depth estimation method combining geometry with a new deep…
Deep Convolutional Neural Networks (CNNs) for image classification successively alternate convolutions and downsampling operations, such as pooling layers or strided convolutions, resulting in lower resolution features the deeper the…
Monocular depth estimation has drawn widespread attention from the vision community due to its broad applications. In this paper, we propose a novel physics (geometry)-driven deep learning framework for monocular depth estimation by…
Deep neural networks face many problems in the field of hyperspectral image classification, lack of effective utilization of spatial spectral information, gradient disappearance and overfitting as the model depth increases. In order to…
Depth Estimation has wide reaching applications in the field of Computer vision such as target tracking, augmented reality, and self-driving cars. The goal of Monocular Depth Estimation is to predict the depth map, given a 2D monocular RGB…
We study performance characteristics of convolutional neural networks (CNN) for mobile computer vision systems. CNNs have proven to be a powerful and efficient approach to implement such systems. However, the system performance depends…
There is an increasing interest in applying deep learning to 3D mesh segmentation. We observe that 1) existing feature-based techniques are often slow or sensitive to feature resizing, 2) there are minimal comparative studies and 3)…
Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…
Deep neural networks (DNNs) have achieved great success in the area of computer vision. The disparity estimation problem tends to be addressed by DNNs which achieve much better prediction accuracy than traditional hand-crafted feature-based…
We present a novel approach for estimating depth from a monocular camera as it moves through complex and crowded indoor environments, e.g., a department store or a metro station. Our approach predicts absolute scale depth maps over the…
Monocular 3D lane detection is essential for autonomous driving, but challenging due to the inherent lack of explicit spatial information. Multi-modal approaches rely on expensive depth sensors, while methods incorporating fully-supervised…
Monocular depth estimation is a highly challenging problem that is often addressed with deep neural networks. While these are able to use recognition of image features to predict reasonably looking depth maps the result often has low metric…
Deep neural networks (DNNs) are state-of-the-art techniques for solving most computer vision problems. DNNs require billions of parameters and operations to achieve state-of-the-art results. This requirement makes DNNs extremely compute,…
Image-based depth estimation has gained significant attention in recent research on computer vision for autonomous vehicles in intelligent transportation systems. This focus stems from its cost-effectiveness and wide range of potential…