2025计算机视觉论文综述汇总

admin 管理员组

文章数量: 1184232

2025.5.23 分类由AI生成

1. 遥感图像处理

• 遥感基础模型：
• A Survey on Remote Sensing Foundation Models-- From Vision to Multimodality --2503.22081v1.pdf
• MIMRS-- A Survey on Masked Image Modeling in Remote Sensing – 2504.03181v2.pdf
• Vision Mamba in Remote Sensing-- A Comprehensive Survey of Techniques, Applications and Outlook – 2505.00630v2.pdf
• 遥感图像变化检测：
• A Survey of Sample-Efficient Deep Learning for Change Detection in Remote Sensing-- Tasks, Strategies, and Challenges – 2502.02835v1.pdf
• SAR 舰船分类：
• A Survey on SAR ship classification using Deep Learning – 2503.11906v1.pdf
• 卫星AI图像处理：
• Advancing Earth Observation-- A Survey on AI-Powered Image Processing in Satellites – 2501.12030v1.pdf
• 精准农业：
• Vision Transformers in Precision Agriculture-- A Comprehensive Survey – 2504.21706v2.pdf
• A survey of datasets for computer vision in agriculture – 2502.16950v1.pdf

2. 医学图像处理

• 医学图像重建：
• A Comprehensive Survey on Magnetic Resonance Image Reconstruction – 2503.07097v1.pdf
• A Survey of fMRI to Image Reconstruction – 2502.16861v1.pdf
• A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli – 2503.15978v1.pdf
• 医学图像分割：
• Recent Advances in Medical Imaging Segmentation-- A Survey – 2505.09274v1.pdf
• Self-Supervised Learning for Image Segmentation: A Comprehensive Survey – 2505.13584v1.pdf 总结
• 医学图像到网格重建：
• From Pixels to Polygons-- A Survey of Deep Learning Approaches for Medical Image-to-Mesh Reconstruction – 2505.03599v1.pdf
• 医学图像深度学习（通用）：
• Deep Learning Approaches for Medical Imaging Under Varying Degrees of Label Availability-- A Comprehensive Survey – 2504.11588v1.pdf
• 病理学基础模型：
• A Survey of Pathology Foundation Model-- Progress and Future Directions – 2504.04045v2.pdf
• A Survey on Computational Pathology Foundation Models-- Datasets, Adaptation Strategies, and Evaluation Tasks – 2501.15724v2.pdf
• 计算神经影像学：
• Diffusion Models for Computational Neuroimaging-- A Survey – 2502.06552v1.pdf
• 视网膜成像/眼科学：
• The Eye as a Window to Systemic Health-- A Survey of Retinal Imaging from Classical Techniques to Oculomics – 2505.04006v1.pdf
• 医学图像中的 Transformers：
• Transformers in Medical Imaging-- A Survey – 2201.09873v1.pdf

3. 点云处理 / 3D 视觉

• 3D 配准：
• 3D Registration in 30 Years-- A Survey – 2412.13735v2.pdf
• 3D 场景生成：
• 3D Scene Generation-- A Survey – 2505.05474v1.pdf
• 事件驱动3D重建：
• A Survey on Event-driven 3D Reconstruction-- Development under Different Categories – 2503.19753v2.pdf
• 自动驾驶中的学习型3D重建：
• Learning-based 3D Reconstruction in Autonomous Driving-- A Comprehensive Survey – 2503.14537v2.pdf
• 3D 点云基础模型：
• Foundational Models for 3D Point Clouds-- A Survey and Outlook – 2501.18594v1.pdf
• 辐射场隐式和显式表示：
• Editing Implicit and Explicit Representations of Radiance Fields-- A Survey – 2412.17628v1.pdf
• 神经辐射场 (NeRF)：
• Neural Radiance Fields for the Real World-- A Survey – 2501.13104v1.pdf
• 点云场景分割：
• Point Cloud Based Scene Segmentation-- A Survey – 2503.12595v1.pdf
• 点云语义信息隐式引导与显式表示：
• Implicit Guidance and Explicit Representation of Semantic Information in Points Cloud-- A Survey – 2501.05473v1.pdf

4. 视频处理

• 视频生成：
• A Comprehensive Survey on Generative AI for Video-to-Music Generation – 2502.12489v1.pdf
• A Survey of Interactive Generative Video – 2504.21853v1.pdf
• Survey of Video Diffusion Models-- Foundations, Implementations, and Applications – 2504.16081v1.pdf
• Exploring the Evolution of Physics Cognition in Video Generation-- A Survey – 2503.21765v1.pdf
• 视频到音乐生成：
• Vision-to-Music Generation-- A Survey – 2503.21254v1.pdf
• 动作质量评估：
• A Comprehensive Survey of Action Quality Assessment-- Method and Benchmark – 2412.11149v1.pdf
• A Decade of Action Quality Assessment-- Largest Systematic Survey of Trends, Challenges, and Future Directions – 2502.02817v1.pdf
• 动作识别：
• SMART-Vision-- Survey of Modern Action Recognition Techniques in Vision – 2501.13066v1.pdf
• 云边端协同系统中的视频分析：
• A Survey on Video Analytics in Cloud-Edge-Terminal Collaborative Systems – 2502.06581v4.pdf
• 4D 生成：
• Advances in 4D Generation-- A Survey – 2503.14501v2.pdf
• 3D 理解中的具身智能（视频相关）：
• Embodied Intelligence for 3D Understanding-- A Survey on 3D Scene Question Answering – 2502.00342v1.pdf
• SAM2 图像和视频分割：
• SAM2 for Image and Video Segmentation-- A Comprehensive Survey – 2503.12781v1.pdf

5. 普通图像处理与计算机视觉

• 图像增强：
• A Comprehensive Survey on Image Signal Processing Approaches for Low-Illumination Image Enhancement – 2502.05995v1.pdf
• Underwater Image Enhancement using Generative Adversarial Networks-- A Survey – 2501.06273v1.pdf
• Survey on Single-Image Reflection Removal using Deep Learning Techniques – 2502.08836v1.pdf
• 图像质量评估：
• A Survey on Image Quality Assessment-- Insights, Analysis, and Future Outlook – 2502.08540v1.pdf
• 图像分割：
• SAM2 for Image and Video Segmentation: A Comprehensive Survey – 2503.12781v1.pdf
• 目标检测：
• Small Object Detection-- A Comprehensive Survey on Challenges, Techniques and Real-World Applications – 2503.20516v1.pdf
• 边缘检测：
• Hybrid Multi-Stage Learning Framework for Edge Detection-- A Survey – 2503.21827v1.pdf
• 图像反演：
• Image Inversion-- A Survey from GANs to Diffusion and Beyond – 2502.11974v1.pdf
• 图像识别：
• Image Recognition with Online Lightweight Vision Transformer-- A Survey – 2505.03113v2.pdf
• 云服务中面部图像隐私保护：
• A Survey on Facial Image Privacy Preservation in Cloud-Based Services – 2501.08665v1.pdf
• 生成对抗网络 (GANs)：
• Generative Adversarial Networks with Limited Data-- A Survey and Benchmarking – 2504.05456v1.pdf
• 工业异常合成：
• A Survey on Industrial Anomalies Synthesis – 2502.16412v1.pdf
• 手写文本识别：
• Handwritten Text Recognition-- A Survey – 2502.08417v1.pdf
• 单目度量深度估计：
• Survey on Monocular Metric Depth Estimation – 2501.11841v3.pdf
• 基于事件的成像：
• From Events to Enhancement-- A Survey on Event-Based Imaging Technologies – 2505.05488v1.pdf
• A Survey on Event-based Optical Marker Systems – 2504.20736v1.pdf
• Towards Mobile Sensing with Event Cameras on High-agility Resource-constrained Devices-- A Survey – 2503.22943v2.pdf
• 视觉数据数字孪生生成：
• Digital Twin Generation from Visual Data-- A Survey – 2504.13159v1.pdf
• 时尚新品性能预测：
• New Fashion Products Performance Forecasting-- A Survey on Evolutions, Models and Emerging Trends – 2501.10324v1.pdf

6. 大型视觉-语言模型 (LVLMs) / 多模态 AI

• LVLM 对齐与安全：
• A Survey of Safety on Large Vision-Language Models-- Attacks, Defenses and Evaluations – 2502.14881v1.pdf
• A Survey of State of the Art Large Vision Language Models-- Alignment, Benchmark, Evaluations and Challenges – 2501.02189v6.pdf
• Large Vision-Language Model Alignment and Misalignment-- A Survey Through the Lens of Explainability – 2501.01346v2.pdf
• Aligning Multimodal LLM with Human Preference-- A Survey – 2503.14504v2.pdf
• When Data Manipulation Meets Attack Goals-- An In-depth Survey of Attacks for VLMs – 2502.06390v2.pdf
• 高效 LVLM：
• A Survey on Efficient Vision-Language Models – 2504.09724v1.pdf
• Small Vision-Language Models-- A Survey on Compact Architectures and Techniques – 2503.10665v1.pdf
• Vision-Language Models for Edge Networks-- A Comprehensive Survey – 2502.07855v1.pdf
• LVLM 集成与 LLM 视觉能力赋能：
• Efficiently Integrate Large Language Models with Visual Perception-- A Survey from the Training Paradigm Perspective – 2502.01524v1.pdf
• How Vision-Language Tasks Benefit from Large Pre-trained Models-- A Survey – 2412.08158v1.pdf
• How to Enable LLM with 3D Capacity-- A Survey of Spatial Reasoning in LLM – 2504.05786v1.pdf
• 多模态思维链推理：
• Multimodal Chain-of-Thought Reasoning-- A Comprehensive Survey – 2503.12605v2.pdf
• 多模态数据增强：
• Multimodal Large Language Models for Image, Text, and Speech Data Augmentation-- A Survey – 2501.18648v2.pdf
• 多模态融合与机器人视觉：
• Multimodal Fusion and Vision-Language Models-- A Survey for Robot Vision – 2504.02477v1.pdf
• 多模态生成模型：
• Simulating the Real World-- A Unified Survey of Multimodal Generative Models – 2503.04641v1.pdf
• 下一词预测迈向多模态智能：
• Next Token Prediction Towards Multimodal Intelligence-- A Comprehensive Survey – 2412.18619v2.pdf
• 大型多模态模型数据集、应用类别与分类：
• Survey of Large Multimodal Model Datasets, Application Categories and Taxonomy – 2412.17759v1.pdf
• AI 生成媒体检测（与 MLLM 相关）：
• Survey on AI-Generated Media Detection-- From Non-MLLM to MLLM – 2502.05240v2.pdf
• 视觉问答：
• A Comprehensive Survey of Knowledge-Based Vision Question Answering Systems-- The Lifecycle of Knowledge in Visual Reasoning Task – 2504.17547v1.pdf
• Visual question answering-- from early developments to recent advances – a survey – 2501.03939v2.pdf
• 视觉 grounding：
• Towards Visual Grounding-- A Survey – 2412.20206v1.pdf

7. 生成式 AI（超越文本到图像/视频）

• 生成式 AI 用于电影创作：
• Generative AI for Film Creation-- A Survey of Recent Advances – 2504.08296v1.pdf
• 生成式 AI 用于赛璐珞动画：
• Generative AI for Cel-Animation-- A Survey – 2501.06250v1.pdf
• 生成式 AI 用于角色动画：
• Generative AI for Character Animation-- A Comprehensive Survey of Techniques, Applications, and Future Directions – 2504.19056v1.pdf
• 生成式物理 AI：
• Generative Physical AI in Vision-- A Survey – 2501.10928v2.pdf
• 深度生成模型个性化图像生成：
• Personalized Image Generation with Deep Generative Models-- A Decade Survey – 2502.13081v1.pdf

8. 扩散模型

• 扩散模型中的概念擦除：
• A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models – 2502.14896v1.pdf
• 扩散模型中的视觉概念挖掘：
• A Comprehensive Survey on Visual Concept Mining in Text-to-image Diffusion Models – 2503.13576v1.pdf
• 扩散模型中的注意力机制：
• Attention in Diffusion Model-- A Survey – 2504.03738v1.pdf
• 扩散模型上的偏好对齐：
• Preference Alignment on Diffusion Model-- A Comprehensive Survey for Image Generation and Editing – 2502.07829v1.pdf
• 文本到图像生成与编辑（扩散模型）：
• Text to Image Generation and Editing-- A Survey – 2505.02527v1.pdf

9. 计算机视觉架构与技术（通用）

• 深度 CNN：
• A Comprehensive Survey on Architectural Advances in Deep CNNs-- Challenges, Applications, and Emerging Research Directions – 2503.16546v1.pdf
• 视觉 Transformers：
• Vision Transformers on the Edge-- A Comprehensive Survey of Model Compression and Acceleration Strategies – 2503.02891v3.pdf
• Mamba 架构在视觉应用中：
• A Survey on Mamba Architecture for Vision Applications – 2502.07161v1.pdf
• 动态神经网络：
• A Survey on Dynamic Neural Networks-- from Computer Vision to Multi-modal Sensor Fusion – 2501.07451v1.pdf
• 对抗性防御：
• A Survey of Adversarial Defenses in Vision-based Systems-- Categorization, Methods and Challenges – 2503.00384v1.pdf
• 全向视觉中的表示学习：
• A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision – 2502.10444v1.pdf
• 自监督对比学习：
• A Survey on Data Curation for Visual Contrastive Learning-- Why Crafting Effective Positive and Negative Pairs Matters – 2502.08134v1.pdf
• A Survey on Self-supervised Contrastive Learning for Multimodal Text-Image Analysis – 2503.11101v2.pdf
• 序数回归：
• A Survey on Ordinal Regression-- Applications, Advances and Prospects – 2503.00952v1.pdf
• 类别无关计数：
• A Survey on Class-Agnostic Counting-- Advancements from Reference-Based to Open-World Text-Guided Approaches – 2501.19184v3.pdf
• 小样本不平衡问题：
• A Survey on Small Sample Imbalance Problem-- Metrics, Feature Analysis, and Solutions – 2504.14800v1.pdf
• 域外检测：
• Recent Advances in Out-of-Distribution Detection with CLIP-Like Models-- A Survey – 2505.02448v1.pdf
• 鲁棒非可转移学习：
• Toward Robust Non-Transferable Learning-- A Survey and Benchmark – 2502.13593v2.pdf
• 工业缺陷检测（基础模型）：
• A Survey on Foundation-Model-Based Industrial Defect Detection – 2502.19106v2.pdf
• 人机交互运动生成：
• A Survey on Human Interaction Motion Generation – 2503.12763v2.pdf
• 图像语义描述模型：
• A Preliminary Survey of Semantic Descriptive Model for Images – 2501.08352v1.pdf
• 利用视觉模型进行时间序列分析：
• Harnessing Vision Models for Time Series Analysis-- A Survey – 2502.08869v1.pdf
• 设备上基于视觉的裂缝检测的量化技术：
• Survey of Quantization Techniques for On-Device Vision-based Crack Detection – 2502.02269v1.pdf
• 视觉输入手势识别：
• Survey on Hand Gesture Recognition from Visual Input – 2501.11992v1.pdf
• 视觉基础模型的解释性：
• Explainability for Vision Foundation Models-- A Survey – 2501.12203v1.pdf
• 组合图像检索：
• A Comprehensive Survey on Composed Image Retrieval – 2502.18495v2.pdf
• Composed Multi-modal Retrieval-- A Survey of Approaches and Applications – 2503.01334v1.pdf
• 视觉中的检索增强生成与理解：
• Retrieval Augmented Generation and Understanding in Vision-- A Survey and New Outlook – 2503.18016v1.pdf

10. 自动驾驶与机器人

• 自动驾驶中的世界模型：
• A Survey of World Models for Autonomous Driving – 2501.11260v2.pdf
• The Role of World Models in Shaping Autonomous Driving-- A Comprehensive Survey – 2502.10498v1.pdf
• 自动驾驶中的联合感知与预测：
• Joint Perception and Prediction for Autonomous Driving-- A Survey – 2412.14088v1.pdf
• 室内具身 AI 中的语义建图：
• Semantic Mapping in Indoor Embodied AI – A Comprehensive Survey and Future Directions – 2501.05750v1.pdf

11. 其他及专业应用

• 掌纹识别：
• Deep Learning in Palmprint Recognition-A Comprehensive Survey – 2501.01166v1.pdf
• 第一人称视觉：
• Challenges and Trends in Egocentric Vision-- A Survey – 2503.15275v2.pdf
• 体育中的动作评估：
• Action Valuation in Sports-- A Survey – 2504.06163v1.pdf
• 反无人机方法：
• Securing the Skies-- A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions – 2504.11967v2.pdf
• 360 度全景图生成：
• A Survey on Text-Driven 360-Degree Panorama Generation – 2502.14799v1.pdf
• VideoLLM 基准与评估：
• VideoLLM Benchmarks and Evaluation-- A Survey – 2505.03829v1.pdf

本文标签： 视觉 计算机 论文