Related papers: SFMNet: Sparse Focal Modulation for 3D Object Dete…

Surface defect inspection plays an important role in the process of industrial manufacture and production. Though Convolutional Neural Network (CNN) based defect inspection methods have made huge leaps, they still confront a lot of…

3D object detection based on LiDAR point clouds is a crucial module in autonomous driving particularly for long range sensing. Most of the research is focused on achieving higher accuracy and these models are not optimized for deployment on…

This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent…

Real-time and high-performance 3D object detection is of critical importance for autonomous driving. Recent top-performing 3D object detectors mainly rely on point-based or 3D voxel-based convolutions, which are both computationally…

Convolutional Neural networks (CNN) have been the first choice of paradigm in many computer vision applications. The convolution operation however has a significant weakness which is it only operates on a local neighborhood of pixels, thus…

Change detection, a critical task in remote sensing and computer vision, aims to identify pixel-level differences between image pairs captured at the same geographic area but different times. It faces numerous challenges such as…

Multi-frame infrared small target detection (IRSTD) plays a crucial role in low-altitude and maritime surveillance. The hybrid architecture combining CNNs and Transformers shows great promise for enhancing multi-frame IRSTD performance. In…

Change detection, i.e. identification per pixel of changes for some classes of interest from a set of bi-temporal co-registered images, is a fundamental task in the field of remote sensing. It remains challenging due to unrelated forms of…

Accurate and robust detection of multi-class objects in optical remote sensing images is essential to many real-world applications such as urban planning, traffic control, searching and rescuing, etc. However, state-of-the-art object…

Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust correspondences under…

Recent years have seen an increase in the use of gigapixel-level image and video capture systems and benchmarks with high-resolution wide (HRW) shots. However, unlike close-up shots in the MS COCO dataset, the higher resolution and wider…

Salient Object Detection (SOD) has traditionally relied on feature refinement modules that utilize the features of an ImageNet pre-trained backbone. However, this approach limits the possibility of pre-training the entire network because of…

Medical image segmentation, a crucial task in computer vision, facilitates the automated delineation of anatomical structures and pathologies, supporting clinicians in diagnosis, treatment planning, and disease monitoring. Notably,…

With the rapid development of deep learning, a variety of change detection methods based on deep learning have emerged in recent years. However, these methods usually require a large number of training samples to train the network model, so…

Lane detection is a fundamental task in autonomous driving, and has achieved great progress as deep learning emerges. Previous anchor-based methods often design dense anchors, which highly depend on the training dataset and remain fixed…

Remote sensing images captured from aerial perspectives often exhibit significant scale variations and complex backgrounds, posing challenges for salient object detection (SOD). Existing methods typically extract multi-level features at a…

We present Dense-SfM, a novel Structure from Motion (SfM) framework designed for dense and accurate 3D reconstruction from multi-view images. Sparse keypoint matching, which traditional SfM methods often rely on, limits both accuracy and…

Recent trackers adopt the Transformer to combine or replace the widely used ResNet as their new backbone network. Although their trackers work well in regular scenarios, however, they simply flatten the 2D features into a sequence to better…

The deployment of transformers for visual object tracking has shown state-of-the-art results on several benchmarks. However, the transformer-based models are under-utilized for Siamese lightweight tracking due to the computational…

Deploying deep learning models on embedded systems has been challenging due to limited computing resources. The majority of existing work focuses on accelerating image classification, while other fundamental vision problems, such as object…