Related papers: MonoMM: A Multi-scale Mamba-Enhanced Network for R…

Compared to typical multi-sensor systems, monocular 3D object detection has attracted much attention due to its simple configuration. However, there is still a significant gap between LiDAR-based and monocular-based methods. In this paper,…

Mamba-based vision models have gained extensive attention as a result of being computationally more efficient than attention-based models. However, spatial redundancy still exists in these models, represented by token and block redundancy.…

Multispectral fusion object detection is a critical task for edge-based maritime surveillance and remote sensing, demanding both high inference efficiency and robust feature representation for high-resolution inputs. However, current State…

Recent advancements in sequence modeling have led to the development of the Mamba architecture, noted for its selective state space approach, offering a promising avenue for efficient long sequence handling. However, its application in 3D…

3D object detection is critical for autonomous driving, yet it remains fundamentally challenging to simultaneously maximize computational efficiency and capture long-range spatial dependencies. We observed that Mamba-based models, with…

Recent 2D CNN-based domain adaptation approaches struggle with long-range dependencies due to limited receptive fields, making it difficult to adapt to target domains with significant spatial distribution changes. While transformer-based…

Target detection in high-resolution remote sensing imagery faces challenges due to the low recognition accuracy of small targets and high computational costs. The computational complexity of the Transformer architecture increases…

3D object detection with a single image is an essential and challenging task for autonomous driving. Recently, keypoint-based monocular 3D object detection has made tremendous progress and achieved great speed-accuracy trade-off. However,…

Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D…

State-of-the-art video object detection methods maintain a memory structure, either a sliding window or a memory queue, to enhance the current frame using attention mechanisms. However, we argue that these memory structures are not…

Multimodal medical image fusion plays an instrumental role in several areas of medical image processing, particularly in disease recognition and tumor detection. Traditional fusion methods tend to process each modality independently before…

Robust feature representations are essential for learning-based Multi-View Stereo (MVS), which relies on accurate feature matching. Recent MVS methods leverage Transformers to capture long-range dependencies based on local features…

Sonar imaging is the primary modality for underwater target detection, yet small targets remain difficult to detect due to insufficient pixel coverage, low acoustic contrast, and scale ambiguity across imaging ranges. CNN-based detectors…

Pan-sharpening aims to generate high-resolution multispectral (HRMS) images by integrating a high-resolution panchromatic (PAN) image with its corresponding low-resolution multispectral (MS) image. To achieve effective fusion, it is crucial…

Monocular 3D object detection reveals an economical but challenging task in autonomous driving. Recently center-based monocular methods have developed rapidly with a great trade-off between speed and accuracy, where they usually depend on…

Multi-view depth estimation has achieved impressive performance over various benchmarks. However, almost all current multi-view systems rely on given ideal camera poses, which are unavailable in many real-world scenarios, such as autonomous…

Current end-to-end multi-modal models utilize different encoders and decoders to process input and output information. This separation hinders the joint representation learning of various modalities. To unify multi-modal processing, we…

Mapping and 3D detection are two major issues in vision-based robotics, and self-driving. While previous works only focus on each task separately, we present an innovative and efficient multi-task deep learning framework (SM3D) for…

Existing deep learning-based approaches for monocular 3D object detection in autonomous driving often model the object as a rotated 3D cuboid while the object's geometric shape has been ignored. In this work, we propose an approach for…

Compared to single view medical image classification, using multiple views can significantly enhance predictive accuracy as it can account for the complementarity of each view while leveraging correlations between views. Existing multi-view…