Beihang University（北京航空航天大学）；State Key Laboratory of High-Efficiency Reusable Aerospace Transportation Technology（高效可重复使用航天运输技术国家重点实验室）；The School of Astronautics（航天学院）；The National Key Laboratory of Integrated Air-Ground Navigation Technologies（集成空天地导航技术国家实验室）；The State Key Laboratory of Media Convergence and Communication（媒体融合与传播国家重点实验室）；The School of Artificial Intelligence（人工智能学院）；Zhongguancun Academy（中关村学院）；The School of Automation Science and Electrical Engineering（自动化科学与电气工程学院）；Beijing Institute of Control and Electronics Technology（北京控制电子技术研究所）；Ningbo Institute of Digital Twin（宁波数字孪生研究所）；Eastern Institute of Technology（东部技术研究所）；Hangzhou Research Institute, School of Artificial Intelligence（杭州研究院，人工智能学院）
The complementary information between RGB and IR images can significantly enhance object detection performance under extreme conditions. Existing methods prefer dual-stream CNN backbones built upon YOLO for feature extraction and focus on the design of feature fusion. In this paper, we introduce the Laplacian Decoupled Feature Enhancement block (LDFE) to fuse features from different stages of the dual-stream CNN backbone. By design, LDFE simultaneously considers the characteristics of modalities and structures for feature fusion by employing global-local decomposition, denoising, fusion, and reconstruction, sequentially. The LDFE first separates features into global and local components based on Laplacian Pyramid, and then performs denoising and fusion based on Global State Space Enhancement module (GS2E) and Local Convolutional Correlation Enhancement module (LC2E) separately. Specifically, the GS2E conducts a two-branch architecture for the main and auxiliary modalities. It dynamically suppresses noise in the main modality through cross-modal attention derived from the auxiliary modality, while employing a State Space Model to capture long-range dependencies within the global feature representations of the main modality. To obtain bidirectional interaction, the two modalities systematically alternate their main/auxiliary roles. Moreover, the LC2E suppresses noise in local features and leverages spatial and channel dimension along with triple convolution to extract fine-grained details for fusion. These innovative designs achieve a significant performance improvement, with mAP surpassing the SOTA methods 6.2%, 3.7%, 4.7%, 2.3%, 4.1% and 2.0% on M3FD, DroneVehicle, LLVIP, FLIR-Aligned, KAIST and VEDAI datasets,respectively.
SAMSOD: Rethinking SAM Optimization for RGB-T Salient Object Detection
Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, School of Computer Science and Technology, Anhui University（教育部智能计算与信号处理重点实验室，计算机科学与技术学院，安徽大学）
The Chinese University of Hong Kong（香港中文大学）；Sensetime Group Limited（商汤集团有限公司）
Monocular 3D object detection task aims to predict the 3D bounding boxes of objects based on monocular RGB images. Since the location recovery in 3D space is quite difficult on account of absence of depth information, this paper proposes a novel unified framework which decomposes the detection problem into a structured polygon prediction task and a depth recovery task. Different from the widely studied 2D bounding boxes, the proposed novel structured polygon in the 2D image consists of several projected surfaces of the target object. Compared to the widely-used 3D bounding box proposals, it is…
DEYOLO: Dual-Feature-Enhancement YOLO for Cross-Modality Object Detection
College of Artificial Intelligence, Nankai University（南开大学人工智能学院）；Engineering Research Center of Trusted Behavior Intelligence, Ministry of Education, Nankai University（南开大学教育部可信行为智能工程研究中心）
Huazhong University of Science and Technology（华中科技大学）
Pixel-wise prediction with deep neural network has become an effective paradigm for salient object detection (SOD) and achieved remarkable performance. However, very few SOD models are robust against adversarial attacks which are visually imperceptible for human visual attention. The previous work robust saliency (ROSA) shuffles the pre-segmented superpixels and then refines the coarse saliency map by the densely connected conditional random field (CRF). Different from ROSA that relies on various pre- and post-processings, this paper proposes a light-weight Learnable Noise (LeNo) to defend adv…
Renmin University of China（中国人民大学）；Nanjing University of Science and Technology（南京理工大学）；Nreal；Tsinghua University（清华大学）
Recently, RGBD-based category-level 6D object pose estimation has achieved promising improvement in performance, however, the requirement of depth information prohibits broader applications. In order to relieve this problem, this paper proposes a novel approach named Object Level Depth reconstruction Network (OLD-Net) taking only RGB images as input for category-level 6D object pose estimation. We propose to directly predict object-level depth from a monocular RGB image by deforming the category-level shape prior into object-level depth and the canonical NOCS representation. Two novel modules …
FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model for SAR Imagery
Fudan University（复旦大学）；Discipline and Technology Center of Microwave Vision Intelligent Sensing, Fudan University（微波视觉智能感知学科与技术中心，复旦大学）；Shanghai Innovation Institute（上海创新研究院）
Decoupling Amplitude and Phase Attention in Frequency Domain for RGB-Event based Visual Object Tracking
School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）；Northeastern University（东北大学）；Beijing Institute of Technology（北京理工大学）；School of Computer and Communication Engineering, University of Science and Technology Beijing（北京科技大学计算机与通信工程学院）；Peng Cheng Laboratory（鹏城实验室）；National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University（北京大学多媒体信息处理国家重点实验室）；School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University（北京大学深圳研究生院电子与计算机工程学院）
University of Birmingham（伯明翰大学）；Shenzhen University（深圳大学）
In this paper, we focus on category-level 6D pose and size estimation from monocular RGB-D image. Previous methods suffer from inefficient category-level pose feature extraction which leads to low accuracy and inference speed. To tackle this problem, we propose a fast shape-based network (FS-Net) with efficient category-level feature extraction for 6D pose estimation. First, we design an orientation aware autoencoder with 3D graph convolution for latent feature extraction. The learned latent feature is insensitive to point shift and object size thanks to the shift and scale-invariance properti…
Cross-scene model adaption is crucial for camera relocalization in real scenarios. It is often preferable that a pre-learned model can be fast adapted to a novel scene with as few training samples as possible. The existing state-of-the-art approaches, however, can hardly support such few-shot scene adaption due to the entangling of image feature extraction and scene coordinate regression. To address this issue, we approach camera relocalization with a decoupled solution where feature extraction, coordinate regression, and pose estimation are performed separately. Our key insight is that featur…
MCL-AD: Multimodal Collaboration Learning for Zero-Shot 3D Anomaly Detection
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan)（计算能力网络与信息安全部教育部重点实验室，山东计算机科学中心（济南国家超级计算机中心））；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东科学院））；Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science（山东省计算能力互联网与服务计算重点实验室，山东省计算机科学基础研究中心）
GMBFormer: An NDVI-Guided Global Memory Bank Transformer for Urban Green-Space Extraction from Ultra-High-Resolution Imagery
College of Geophysics, Chengdu University of Technology（成都理工大学地球物理学院）；National Engineering Research Center for Geomatics, Aerospace Information Research Institute, Chinese Academy of Sciences, and University of Chinese Academy of Sciences（中国科学院测绘学部国家工程研究中心、航天信息研究院、中国科学院大学）
SurgSora: Object-Aware Diffusion Model for Controllable Surgical Video Generation
The University of Sydney, Sydney, Australia（悉尼大学）；The University of Hong Kong, Hong Kong SAR, China（香港大学）；The Chinese University of Hong Kong, Hong Kong SAR, China（香港中文大学）
MODAL: Multi-Modal Object Re-ID via Model-Driven Sparse Decoupling and Text-Image Differential Filtering
College of Computer Science and Technology, National University of Defense Technology（国防科技大学计算机科学与技术学院）；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）
