English
Related papers

Related papers: DepthMamba with Adaptive Fusion

200 papers

Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Yaohua Zha , Yanzi Wang , Hang Guo , Jinpeng Wang , Tao Dai , Bin Chen , Zhihao Ouyang , Xue Yuerong , Ke Chen , Shu-Tao Xia

Diffusion models have achieved great success in image generation, with the backbone evolving from U-Net to Vision Transformers. However, the computational cost of Transformers is quadratic to the number of tokens, leading to significant…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 Yao Teng , Yue Wu , Han Shi , Xuefei Ning , Guohao Dai , Yu Wang , Zhenguo Li , Xihui Liu

Restoration and enhancement are essential for improving the quality of videos captured under atmospheric turbulence conditions, aiding visualization, object detection, classification, and tracking in surveillance systems. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Paul Hill , Zhiming Liu , Nantheera Anantrasirichai

Accurate survival prediction in oncology requires integrating diverse imaging modalities to capture the complex interplay of tumor biology. Traditional single-modality approaches often fail to leverage the complementary insights provided by…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Ho Hin Lee , Alberto Santamaria-Pang , Jameson Merkov , Matthew Lungren , Ivan Tarapov

Shadow removal aims to restore images that are partially degraded by shadows, where the degradation is spatially localized and non-uniform. Unlike general restoration tasks that assume global degradation, shadow removal can leverage…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Linhao Li , Boya Jin , Zizhe Li , Lanqing Guo , Hao Cheng , Bo Li , Yongfeng Dong

In data-scarce scenarios, deep learning models often overfit to noise and irrelevant patterns, which limits their ability to generalize to unseen samples. To address these challenges in medical image segmentation, we introduce Diff-UMamba,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Dhruv Jain , Romain Modzelewski , Romain Herault , Clement Chatelain , Eva Torfeh , Sebastien Thureau

Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions, limiting the exploitation of non-local receptive fields. In response to this issue, we introduce a novel dual-branch…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Shangquan Sun , Wenqi Ren , Juxiang Zhou , Jianhou Gan , Rui Wang , Xiaochun Cao

Unified Multimodal models (UMMs) built on a single architecture have shown impressive performance in both understanding and generation. We identify a fundamental challenge that lies in inductive biases induced by distinct supervision…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Renjie Lu , Xulong Zhang , Xiaoyang Qu , Shangfei Wang , Jianzong Wang

Infrared and visible image fusion aim to integrate modality strengths for visually enhanced, informative images. Visible imaging in real-world scenarios is susceptible to dynamic environmental brightness fluctuations, leading to texture…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Yiming Sun , Bing Cao , Pengfei Zhu , Qinghua Hu

Recent Mamba-based image restoration methods have achieved promising results but remain limited by fixed scanning patterns and inefficient feature utilization. Conventional Mamba architectures rely on predetermined paths that cannot adapt…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Han Hu , Zhuoran Zheng , Liang Li , Chen Lyu

In the field of multi-source remote sensing image classification, remarkable progress has been made by using Convolutional Neural Network (CNN) and Transformer. Recently, Mamba-based methods built upon the State Space Model (SSM) have shown…

Image and Video Processing · Electrical Eng. & Systems 2025-01-28 Feng Gao , Xuepeng Jin , Xiaowei Zhou , Junyu Dong , Qian Du

Detecting hidden or partially concealed objects remains a fundamental challenge in multimodal environments, where factors like occlusion, camouflage, and lighting variations significantly hinder performance. Traditional RGB-based detection…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Harris Song , Tuan-Anh Vu , Sanjith Menon , Sriram Narasimhan , M. Khalid Jawed

3D human pose lifting is a promising research area that leverages estimated and ground-truth 2D human pose data for training. While existing approaches primarily aim to enhance the performance of estimated 2D poses, they often struggle when…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Hu Cui , Tessai Hayama

Self-supervised pretraining is promising for large-scale neuroimaging, yet the impact of region-aware masking and hybrid sequence modeling remains underexplored. In this work, we introduce Rhamba, a region-aware pretraining framework that…

Recent advancements in state space models, notably Mamba, have demonstrated significant progress in modeling long sequences for tasks like language understanding. Yet, their application in vision tasks has not markedly surpassed the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Tao Huang , Xiaohuan Pei , Shan You , Fei Wang , Chen Qian , Chang Xu

Recent advancements in the Mamba architecture, with its linear computational complexity, being a promising alternative to transformer architectures suffering from quadratic complexity. While existing works primarily focus on adapting Mamba…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Jie Hu , Junwei Zheng , Jiale Wei , Jiaming Zhang , Rainer Stiefelhagen

Video anomaly detection (VAD) methods are mostly CNN-based or Transformer-based, achieving impressive results, but the focus on detection accuracy often comes at the expense of inference speed. The emergence of state space models in…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Jiahao Lyu , Minghua Zhao , Jing Hu , Xuewen Huang , Yifei Chen , Shuangli Du

Handling lengthy context is crucial for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs) in applications such as processing high-resolution images or high frame rate videos. The rise in…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Jianing Zhou , Han Li , Shuai Zhang , Ning Xie , Ruijie Wang , Xiaohan Nie , Sheng Liu , Lingyun Wang

Motion planning is a challenging task to generate safe and feasible trajectories in highly dynamic and complex environments, forming a core capability for autonomous vehicles. In this paper, we propose DRAMA, the first Mamba-based…

This paper presents a framework for universal sound separation and polyphonic audio classification, addressing the challenges of separating and classifying individual sound sources in a multichannel mixture. The proposed framework,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-12 Dongheon Lee , Jung-Woo Choi