/Computer-Vision-Tasks-Survey

【CVer出品】旨在盘点最全面的计算机视觉方向

GNU General Public License v3.0GPL-3.0

【CVer出品】旨在盘点最全面的计算机视觉方向

  • 格式:英文(中文翻译)
  • 目前是初版,将不定期补充更多的CV子方向,也欢迎大家提交issues补充。
  • 将陆续附上各个CV子方向的从入门到精通资源,欢迎大家star、watch来支持!

A

  • Adversarial Attacks(对抗攻击)
  • Abnormal Activity Detection
  • Action Detection(行为/动作检测)
    • Online Action Detection(在线行为检测/动作检测)
  • Action Segmentation(行为/动作分割)
  • Action Recognition(行为识别)
  • Adversarial Examples(对抗样本)
  • Airborne LiDAR Point Cloud Classification(机载LiDAR点云分类)
  • Anomaly Detection(异常检测)
  • Abnormal Event Detection(异常事件检测)

B

  • Behavioral Intention Prediction(行为意图预测)
  • Boundary Detection(边界检测)
  • Boundless Unsupervised Domain Adaptation(无界无监督域自适应)
  • Bone Age Assessment(骨龄评估)
  • Blur Detection(模糊检测)

C

  • Camera Localization(视觉)
  • Car Damage Detection(汽车损坏检测)
  • Cell Tracking(细胞跟踪)
  • Channel Pruning(通道剪枝)
  • Cross-domain Crowd Counting(跨域人群计数)
  • Crowd Counting(人群计数)
  • Clothes Retrieval(服装检索)
  • Continual Learning(持续学习)
  • Co-Salient Object Detection(协同显著性目标检测)

D

  • Data Augmentation(数据增广)
  • Dehaze(去雾)
  • Depth Completion(深度补全)
  • Deep Image Prior(图像复原)
  • Defocus Deblurring
  • Depth Estimation(深度估计)
  • Domain Adaptive Person Re-identification(域自适应行人重识别)
  • Document Understanding(文档理解)
  • Distance Metric Learning(度量学习)

E

  • Edge Detection(边缘检测)
  • Eye gaze estimation(眼睛视线估计)
  • Eye Tracking(眼动追踪)

F

  • Face Aging(人脸变老)
  • Face Age Editing(人脸年龄编辑)
  • Face Alignment(人脸对齐)
  • Face Cartoon Generation(人脸卡通画生成)
  • Face Detection(人脸检测)
  • Facial Expression Editing(人脸表情编辑)
  • Facial Expression Recognition(FER,人脸表情识别)
  • Face Parsing(人脸解析)
  • Face Recognition(人脸识别)
  • Face Restoration(人脸复原)
  • Face Renovation(人脸修复)
  • Face Rotation(人脸转正)
  • Face Segmentation(人脸分割)
  • Face Super-Resolution / Hallucination (人脸超分辨率)
  • Facial Motion Capture(面部运动捕捉)
  • Few-Shot Learning
    • Few-Shot Object Detection
    • Few-Shot Semantic Segmentation
  • Fine-Grained Visual Classification(细粒度视觉分类)
  • Font Generation(字体生成)

G

  • Gaze Estimation(视线估计)
  • Gaze Tracking(视线跟踪/眼动跟踪)
  • Generic Event Boundary Detection(通用事件边界检测)
  • Grounded Situation Recognition

H

  • Hand-object Pose Estimation(手持物体姿态估计)
  • Homography Estimation(单应性估计)
  • Human Behavior Understanding(人体行为理解)
  • Human Fall Detection(人体跌倒检测)
  • Human Motion Prediction(人体运动预测)
  • Human Pose Estimation(人体姿态估计)
  • Human Pose Transfer
  • Human Parsing(人体解析)
  • Human Trajectory Prediction(行人轨迹预测)
  • Human-Object Interaction(HOI,"人-物"交互检测)
  • Hyperspectral Image Classification(高光谱图像分类)

I

  • Image Alignment(图像对齐)
  • Image Classifiation(图像分类)
  • Image Captioning(图像描述)
  • Image Colorization(图像着色)
  • Image Completion(图像补全/修复)
  • (JPEG) Image Deblocking(图像去块)
  • Image Copy Detection(图像复制/拷贝检测)
  • Image Deblurring(图像去模糊)
  • Image Demoireing(图像去摩尔纹)
  • Image Fusion(图像融合)
  • Image Inpainting(图像修复/补全)
  • Image Matting(图像抠图)
  • Image Reflection Removal(图像反光去除)
  • Image Rescaling(图像缩放)
  • Image Restoration(图像恢复/复原/修复)
  • Image Retrieval(图像检索)
  • 图像分割(Image Segmentation)
      • 语义分割(Semantic Segmentation)
      • 实例分割(Instance Segmentation)
      • 全景分割(Panoptic Segmentation)
      • 医学图像分割(Medic Image Segmentation)
  • Interactive Image Segmentation(交互式图像分割)
  • Interactive Video Object Segmentation(交互式视频目标分割)

J

  • Joint Denoising and Super-Resolution(联合去噪和超分辨率)

K

  • Knowledge Distillation (知识蒸馏)
  • Knowledge Transfer(知识迁移)

L

  • Landmark Detection(关键点检测)
  • Lane Detection(车道线检测)
  • Lane Graph Estimation(车道图估计)
  • Layout Generation(布局生成)
  • Long-term Visual Tracking (长时视觉跟踪)
  • Low-Light Image Enhancement(低光照图像增强)
  • Low-Light Video Enhancement(低光照视频增强)
  • Light Field Spatial Super-resolution(光场空间超分辨率)
  • Line Detection(线段检测)
  • Line Segment Detector(线段检测)
  • Line Segment Matching(线段匹配)
  • LiDAR Odometry(激光雷达里程计)
  • Low-light Image Enhancement(低光照图像增强)
  • Low-light Raw Image Enhancement(低光照原始图像增强)

M

  • Marine Snow Removal(海雪去除)
  • Makeup Transfer(妆容迁移)
  • Medical
    • Medical Image Classification(医学图像分类)
    • Medical Image Segmentation(医学图像分割)
  • Meta-Learning
  • Motion Deblurring(运动去模糊)
  • Motion Prediction/Forecasting(运动预测)
  • Monocular 6D Object Pose Estimation(单目6D目标姿态估计)
  • Multimodal Deep Learning(多模态深度学习)
  • Multi-focus Image Fusion(多焦距图像融合)

N

  • Natural Language Video Localization

O

  • Object Detection(目标检测)
  • Optical Flow Estimation(光流估计)
  • Object Localization(目标定位)
  • Object Importance Estimation( 目标重要性 )
  • Open-Set Semi-Supervised Object Detection
  • One-Shot Object Detection(One-Shot目标检测)
  • Online Tracking(在线跟踪)
  • Organ at Risk Segmentation(危及器官分割)

P

  • Palmprint Recognition(掌纹识别)
  • Palmprint Verification(掌纹验证)
  • Parking Slot Detection(停车位检测)
  • Part-aware Panoptic Segmentation / Panoptic Part Segmentation(全景Part分割)
  • Pedestrian Detection(行人检测)
  • Pedestrian Attribute Recognition(行人属性识别)
  • Person Search(行人搜索)
    • Pedestrian Detection行人检测+Person Re-identification行人重识别
  • Person Re-identification(行人重识别)
  • Point Cloud Completion(点云补全)
  • Point Cloud Segmentation(点云分割)
  • Point Cloud Semantic Segmentation(点云语义分割)
  • Point Cloud Instance Segmentation(点云实例分割)
  • Point Class(点云分类)

Q

  • Quality Assessment(质量评估)

  • 目标跟踪(Object/Visual Tracking)

R

  • Recognizing Online Handwritten Chinese Characters(OLHCCR,联机手写汉字识别)
  • Referring Image Segmentation(基于文本的实例分割)
  • RGB-D Saliency Detection(RGB-D显著性检测)
  • RGB-D Salient Object Detection(RGB-D显著性目标检测)
  • RGB-T Salient Object Detection(RGB-T显著性目标检测)
  • RGB-D Semantic Segmentation (RGB-D语义分割)
  • Road Curb Detection(道路边界检测)
  • Road Graphs Extraction(道路图提取)
  • Road Marking Segmentation(道路标线分割)
  • Road Segmentation(道路分割)

S

  • Saliency Detection(显著性检测)
  • Saliency Object Detection(显著性目标检测)
  • Salient Object Segmentation(显著性目标分割)
  • Semantic Amodal Segmentation
  • Semantic Correspondence(语义对应)
  • Semantic Image Synthesis(语义图像合成)
  • Semantic Scene Completion(语义场景补全)
  • Semantic Segmentation (语义分割)
  • Semantically Multi-modal Image Synthesis(SMIS,语义多模态图像合成)
  • Semantic manipulation
  • Semi-Supervised Learning
    • Semi-Supervised Object Detection(半监督目标检测)
    • Semi-Supervised Semantic Segmentation(半监督语义分割)
  • Sentiment Transfer(情感迁移)
  • Scene Flow Estimation(场景流估计)
  • Scene Parsing(场景解析)
  • Scene Text Detection(场景文本检测)
  • Scene Text Recognition(场景文本识别)
  • Scene Text Spotting(场景文本检测和识别)
  • Shadow Removal(阴影去除)
  • Soft Color Segmentation(柔和颜色分割)
  • Sign Language Recognition(手语识别)
  • Speech-to-Image Generation(语音-图像生成)
  • Super Resolution(超分辨率)
  • Superpixel Segmentation(超像素分割)
  • Single Image Depth Estimation(单目深度估计)
  • Skeleton-Based Action Recognition(基于骨架的动作识别)
  • Skeleton Extraction(骨架提取)
  • Sketch Segmentation(素描分割)
  • Stereo Matching(立体匹配)
  • Student-Teacher Learning(师-生学习)
  • Surgical Phase Recognition(手术阶段识别)
  • Style Transfer(风格迁移)
  • Small-Sample Classification(小样本分类)
  • Snapshot Compressive Imaging()

T

  • Temporal Action Detection(时序动作检测)
  • Temporal Action Localization(时序动作定位/检测)
  • Temporal Action Proposal Generation(TAPG,时序动作提名生成)
  • Text-to-image Synthesis(文本生成图像)
  • Trajectory Prediction(轨迹预测)
  • Traffic Scene Recognition(交通场景识别)
  • Transparent Object Segmentation(透明物体分割)

U

  • Underwater Object Detector(水下目标检测)
  • Universal Adversarial Perturbations(通用对抗干扰)
  • Unsupervised Domain Adaptation(无监督域自适应)

V

  • Vehicle Re-Identification(车辆重识别)
  • Vehicle Trajectory Prediction(车辆轨迹预测)
  • Vision-and-Language Navigation(视觉-语言导航)
  • Visual Navigation(视觉导航)
  • Video Anomaly Detection(视频异常检测)
  • Video Captioning(视频描述)
  • Video Enhancement(视频增强)
  • Video Object Segmentation(VOS,视频目标分割)
  • Video-based Person Re-identification(视频行人重识别)
  • Video Frame Interpolation(视频插值)
  • Video Salient Object Detection(VOSD,视频显著性目标检测)
  • Video Semantic Segmentation(视频语义分割)
  • Video Summarization(视频摘要)
  • Video Super-Resolution(视频超分辨率)
  • Video Story Question Answering(VSQA,视频故事问答)
  • Video Unsupervised Domain Adaptation(视频无监督域自适应)
  • View Synthesis(视图合成)
  • Visual Commonsense Reasoning(VCR,视觉常识推理)
  • Visual Grounding(视觉定位/落地)
  • Vision-and-Language(视觉-语言)
  • Visual Document Understanding(VDU,视觉文档理解)
  • Visual Dialogue(视觉对话)
  • Visual Hand Pressure Estimation(视觉手压估计)
  • Visual Localization(视觉定位)
  • Video Prediction(视频预测)
  • Visual Question Answering(VQA,视觉问答)
  • Video Question Answering(VideoQA,视频问答)
  • Visual Indoor Navigation(VIN,视觉室内导航)
  • Visual Sentiment Analysis(视觉情感分析)
  • Visual Social Distancing(视觉社交距离)
  • Visual Speech Recognition(视觉语音识别 )
  • Video Moment Retrieval(视频时刻检索)
  • Video Classification(视频分类)
  • Video Inpainting(视频补全)
  • Video Retrieval(视频检索)
  • Visual Relationship Detection(视觉关系检测)
  • Video Restoration(视频恢复)

W

  • Webly Supervised Object Detection(网络监督目标检测)
  • Wireframe Parser(线框分析)
  • Weakly Supervised 3D Semantic Segmentation(弱监督3D语义分割)

X

Y

Z

  • Zer-shot Learning
    • Zero-shot Object Detection
    • Zero-shot Semantic Segmentation

3D

  • 3D Action Recognition(3D行为识别)
  • 3D Face Reconstruction(3D人脸重建)
  • 3D Human Motion Synthesis(3D人体运动合成)
  • 3D Human Reconstruction(3D人体重建)
  • 3D Instance Segmentation(3D实例分割)
  • 3D Object Detection(3D目标检测)
  • 3D Panoptic Segmentation(3D全景分割)
  • 3D Semantic Segmentation(3D语义分割)
  • 3D Shape Classification
  • 3D Medical Image Segmentation(3D医学图像分割)
  • 3D Reconstruction(三维重建)

4D

6D

  • 6D Object Pose Estimation(6D目标姿态估计)