Related papers: Learning to Reduce Information Bottleneck for Obje…
Surface anomaly detection is pivotal for ensuring product quality in industrial manufacturing. While 2D image-based methods have achieved remarkable success, 3D point cloud-based detection remains underexplored despite its richer geometric…
Object detection and tracking are challenging tasks for resource-constrained embedded systems. While these tasks are among the most compute-intensive tasks from the artificial intelligence domain, they are only allowed to use limited…
Instance segmentation is an important task for biomedical and biological image analysis. Due to the complicated background components, the high variability of object appearances, numerous overlapping objects, and ambiguous object…
Camouflaged object detection (COD) aims to segment objects that blend into their surroundings. However, most existing studies overlook the semantic differences among textual prompts of different targets as well as fine-grained frequency…
Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and high-resolution panchromatic (PAN) images. Although deep learning has advanced this field, mainstream…
Recently, biological perception has been a powerful tool for handling the camouflaged object detection (COD) task. However, most existing methods are heavily dependent on the local spatial information of diverse scales from convolutional…
Land cover maps generated from semantic segmentation of high-resolution remotely sensed images have drawn mucon in the photogrammetry and remote sensing research community. Currently, massive fine-resolution remotely sensed (FRRS) images…
Semantic segmentation is one of the core tasks in the field of computer vision, and its goal is to accurately classify each pixel in an image. The traditional Unet model achieves efficient feature extraction and fusion through an…
Spatial redundancy widely exists in visual recognition tasks, i.e., discriminative features in an image or video frame usually correspond to only a subset of pixels, while the remaining regions are irrelevant to the task at hand. Therefore,…
The presence of occlusions has provided substantial challenges to typically-powerful object recognition algorithms. Additional sources of information can be extremely valuable to reduce errors caused by occlusions. Scene context is known to…
Remote sensing object detection (RSOD) often suffers from degradations such as low spatial resolution, sensor noise, motion blur, and adverse illumination. These factors diminish feature distinctiveness, leading to ambiguous object…
Three-dimensional feature extraction is a critical component of autonomous driving systems, where perception tasks such as 3D object detection, bird's-eye-view (BEV) semantic segmentation, and occupancy prediction serve as important…
Transformers have recently emerged as a significant force in the field of image deraining. Existing image deraining methods utilize extensive research on self-attention. Though showcasing impressive results, they tend to neglect critical…
Image restoration aims to recover high-quality images from their corrupted counterparts. Many existing methods primarily focus on the spatial domain, neglecting the understanding of frequency variations and ignoring the impact of implicit…
The drone navigation requires the comprehensive understanding of both visual and geometric information in the 3D world. In this paper, we present a Visual-Geometric Fusion Network(VGF-Net), a deep network for the fusion analysis of…
Object detection is a challenging and popular computer vision problem. The problem is even more challenging in aerial images due to significant variation in scale and viewpoint in a diverse set of object categories. Recently, deep…
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…
The edge computing paradigm places compute-capable devices - edge servers - at the network edge to assist mobile devices in executing data analysis tasks. Intuitively, offloading compute-intense tasks to edge servers can reduce their…
In 2D image processing, some attempts decompose images into high and low frequency components for describing edge and smooth parts respectively. Similarly, the contour and flat area of 3D objects, such as the boundary and seat area of a…
The objective of Few-shot learning is to fully leverage the limited data resources for exploring the latent correlations within the data by applying algorithms and training a model with outstanding performance that can adequately meet the…