Related papers: Using Image Priors to Improve Scene Understanding
Recovering clear structures from severely blurry inputs is a challenging problem due to the large movements between the camera and the scene. Although some works apply segmentation maps on human face images for deblurring, they cannot…
Scene classification is a fundamental perception task for environmental understanding in today's robotics. In this paper, we have attempted to exploit the use of popular machine learning technique of deep learning to enhance scene…
Humans have a remarkable ability to perceive and reason about the world around them by understanding the relationships between objects. In this paper, we investigate the effectiveness of using such relationships for object detection and…
Learning contextual and spatial environmental representations enhances autonomous vehicle's hazard anticipation and decision-making in complex scenarios. Recent perception systems enhance spatial understanding with sensor fusion but often…
Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…
This article studies the problem of image segmentation-based semantic communication in autonomous driving. In real traffic scenes, detecting the key objects (e.g., vehicles, pedestrians and obstacles) is more crucial than that of other…
To navigate through urban roads, an automated vehicle must be able to perceive and recognize objects in a three-dimensional environment. A high-level contextual understanding of the surroundings is necessary to plan and execute accurate…
LiDAR has become a standard sensor for autonomous driving applications as they provide highly precise 3D point clouds. LiDAR is also robust for low-light scenarios at night-time or due to shadows where the performance of cameras is…
LiDARs and cameras are the two main sensors that are planned to be included in many announced autonomous vehicles prototypes. Each of the two provides a unique form of data from a different perspective to the surrounding environment. In…
Semantic scene segmentation plays a critical role in a wide range of robotics applications, e.g., autonomous navigation. These applications are accompanied by specific computational restrictions, e.g., operation on low-power GPUs, at…
Autonomous driving is a safety-critical application, and it is therefore a top priority that the accompanying assistance systems are able to provide precise information about the surrounding environment of the vehicle. Tasks such as 3D…
We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is an Improved Guided Upsampling Module that can replace in toto the decoder part in common semantic segmentation…
In recent years, the concept of artificial intelligence (AI) has become a prominent keyword because it is promising in solving complex tasks. The need for human expertise in specific areas may no longer be needed because machines have…
Driven by deep learning techniques, perception technology in autonomous driving has developed rapidly in recent years, enabling vehicles to accurately detect and interpret surrounding environment for safe and efficient navigation. To…
This paper proposes a convolutional neural network that can fuse high-level prior for semantic image segmentation. Motivated by humans' vision recognition system, our key design is a three-layer generative structure consisting of high-level…
Multi-modal fusion serves as a cornerstone for successful depth map super-resolution. However, commonly used fusion strategies, such as addition and concatenation, fall short of effectively bridging the modal gap. As a result, guided image…
Image semantic segmentation is more and more being of interest for computer vision and machine learning researchers. Many applications on the rise need accurate and efficient segmentation mechanisms: autonomous driving, indoor navigation,…
Current semantic segmentation models cannot easily generalize to new object classes unseen during train time: they require additional annotated images and retraining. We propose a novel segmentation model that injects visual priors into…
Segment Anything Model (SAM) demonstrates powerful zero-shot capabilities; however, its accuracy and robustness significantly decrease when applied to medical image segmentation. Existing methods address this issue through modality fusion,…
Finetuning a pretrained backbone in the encoder part of an image transformer network has been the traditional approach for the semantic segmentation task. However, such an approach leaves out the semantic context that an image provides…