SOTAVerified

Keypoint Detection

Keypoint Detection is essential for analyzing and interpreting images in computer vision. It involves simultaneously detecting and localizing interesting points in an image. Keypoints, also known as interest points, are spatial locations or points in the image that define what is interesting or what stands out. They are invariant to image rotation, shrinkage, translation, distortion, etc. Keypoints examples are body joints, facial landmarks, or any other salient points in objects. Keypoints have uses in problems such as pose estimation, object detection and tracking, facial analysis, and augmented reality.

( Image credit: PifPaf: Composite Fields for Human Pose Estimation; "Learning to surf" by fotologic, license: CC-BY-2.0 )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 339 papers

TitleStatusHype
Sapiens: Foundation for Human Vision ModelsCode9
Images Speak in Images: A Generalist Painter for In-Context Visual LearningCode4
ViTPose++: Vision Transformer for Generic Body Pose EstimationCode3
ViTPose: Simple Vision Transformer Baselines for Human Pose EstimationCode3
RMPE: Regional Multi-person Pose EstimationCode3
Realtime Multi-Person 2D Pose Estimation using Part Affinity FieldsCode3
Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose EstimationCode2
GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual LocalizationCode2
SNAKE: Shape-aware Neural 3D Keypoint FieldCode2
OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal AssociationCode2
X-Pose: Detecting Any KeypointsCode2
Detector-Free Structure from MotionCode2
DaD: Distilled Reinforcement Learning for Diverse Keypoint DetectionCode2
InstructDiffusion: A Generalist Modeling Interface for Vision TasksCode2
A Graph-Based Approach for Category-Agnostic Pose EstimationCode2
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity FieldsCode2
Objects as PointsCode2
SiLK -- Simple Learned KeypointsCode2
DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature MatchingCode2
HoughNet: Integrating near and long-range evidence for visual detectionCode1
DexYCB: A Benchmark for Capturing Hand Grasping of ObjectsCode1
HPRNet: Hierarchical Point Regression for Whole-Body Human Pose EstimationCode1
Deep High-Resolution Representation Learning for Human Pose EstimationCode1
Greedy Offset-Guided Keypoint Grouping for Human Pose EstimationCode1
3D3L: Deep Learned 3D Keypoint Detection and Description for LiDARsCode1
Nonlinear optical encoding enabled by recurrent linear scatteringCode1
2.5D U-Net with Depth Reduction for 3D CryoET Object IdentificationCode1
Center Direction Network for Grasping Point Localization on ClothsCode1
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware SupervisionCode1
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential InformationCode1
Dense Interspecies Face EmbeddingCode1
GRIT: General Robust Image Task BenchmarkCode1
Flowmind2Digital: The First Comprehensive Flowmind Recognition and Conversion ApproachCode1
Few-shot Keypoint Detection with Uncertainty Learning for Unseen SpeciesCode1
Generative Partition Networks for Multi-Person Pose EstimationCode1
EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight TransferCode1
ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor ExtractionCode1
DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single CameraCode1
Explicit Box Detection Unifies End-to-End Multi-Person Pose EstimationCode1
GoodPoint: unsupervised learning of keypoint detection and descriptionCode1
Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint EstimatesCode1
Bottom-Up Human Pose Estimation Via Disentangled Keypoint RegressionCode1
BPFNet: A Unified Framework for Bimodal Palmprint Alignment and FusionCode1
Fast Fourier ConvolutionCode1
CapeX: Category-Agnostic Pose Estimation from Textual Point ExplanationCode1
Cascaded Pyramid Network for Multi-Person Pose EstimationCode1
CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage RefinementCode1
Centroid Distance Keypoint Detector for Colored Point CloudsCode1
A Novel Dataset for Keypoint Detection of quadruped Animals from ImagesCode1
A lightweight 3D dense facial landmark estimation model from position map dataCode1
Show:102550
← PrevPage 1 of 7Next →

No leaderboard results yet.