Related papers: A Multi-Stream Fusion Network for Image Splicing L…
Robots operating in unstructured environments require a comprehensive understanding of their surroundings, necessitating geometric and semantic information from sensor data. Traditional RGB-D processing pipelines focus primarily on…
Among the many possible approaches for the parallelization of self-organizing networks, and in particular of growing self-organizing networks, perhaps the most common one is producing an optimized, parallel implementation of the standard…
Robust road segmentation is a key challenge in self-driving research. Though many image-based methods have been studied and high performances in dataset evaluations have been reported, developing robust and reliable road segmentation is…
Capturing and reconstructing high-speed dynamic 3D scenes has numerous applications in computer graphics, vision, and interdisciplinary fields such as robotics, aerodynamics, and evolutionary biology. However, achieving this using a single…
As image recognition models become more prevalent, scalable coding methods for machines and humans gain more importance. Applications of image recognition models include traffic monitoring and farm management. In these use cases, the…
Infrared and visible image fusion aims to generate synthetic images simultaneously containing salient features and rich texture details, which can be used to boost downstream tasks. However, existing fusion methods are suffering from the…
The advancements in the field of AI is increasingly giving rise to various threats. One of the most prominent of them is the synthesis and misuse of Deepfakes. To sustain trust in this digital age, detection and tagging of deepfakes is very…
General object grasping is an important yet unsolved problem in the field of robotics. Most of the current methods either generate grasp poses with few DoF that fail to cover most of the success grasps, or only take the unstable depth image…
This paper introduces a simple but highly efficient ensemble for robust texture classification, which can effectively deal with translation, scale and changes of significant viewpoint problems. The proposed method first inherits the spirit…
Reasoning-based approaches have demonstrated their powerful ability for the task of image-text matching. In this work, two issues are addressed for image-text matching. First, for reasoning processing, conventional approaches have no…
Simultaneous Localization and Mapping using RGB-D cameras has been a fertile research topic in the latest decade, due to the suitability of such sensors for indoor robotics. In this paper we propose a direct RGB-D SLAM algorithm with…
For real-time semantic segmentation, how to increase the speed while maintaining high resolution is a problem that has been discussed and solved. Backbone design and fusion design have always been two essential parts of real-time semantic…
The existing fusion based RGB-D salient object detection methods usually adopt the bi-stream structure to strike the fusion trade-off between RGB and depth (D). The D quality usually varies from scene to scene, while the SOTA bi-stream…
We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach. From an input monocular RGB video, the video frames are processed by a transformer network that fuses the observations into a volumetric feature grid…
Accurate fovea localization is essential for analyzing retinal diseases to prevent irreversible vision loss. While current deep learning-based methods outperform traditional ones, they still face challenges such as the lack of local…
Spectral clustering approaches have led to well-accepted algorithms for finding accurate clusters in a given dataset. However, their application to large-scale datasets has been hindered by computational complexity of eigenvalue…
This paper puts forth a multi-stream networking paradigm, referred to as soft-source-information-combining (SSIC), to support wireless Internet of Things (IoT) applications with ultra-reliability requirements. For SSIC networking, an SSIC…
Image translation is a computer vision task that involves translating one representation of the scene into another. Various approaches have been proposed and achieved highly desirable results. Nevertheless, its accomplishment requires…
Simulating sonar devices requires modeling complex underwater acoustics, simultaneously rendering time-efficient data. Existing methods focus on basic implementation of one sonar type, where most of sound properties are disregarded. In this…
The classification of indoor scenes is a critical component in various applications, such as intelligent robotics for assistive living. While deep learning has significantly advanced this field, models often suffer from reduced performance…