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
DaD: Distilled Reinforcement Learning for Diverse Keypoint DetectionCode2
GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual LocalizationCode2
Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose EstimationCode2
A Graph-Based Approach for Category-Agnostic Pose EstimationCode2
X-Pose: Detecting Any KeypointsCode2
InstructDiffusion: A Generalist Modeling Interface for Vision TasksCode2
DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature MatchingCode2
Detector-Free Structure from MotionCode2
SiLK -- Simple Learned KeypointsCode2
SNAKE: Shape-aware Neural 3D Keypoint FieldCode2
OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal AssociationCode2
Objects as PointsCode2
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity FieldsCode2
TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor LearningCode1
Why Not Replace? Sustaining Long-Term Visual Localization via Handcrafted-Learned Feature Collaboration on CPUCode1
REF-VLM: Triplet-Based Referring Paradigm for Unified Visual DecodingCode1
2.5D U-Net with Depth Reduction for 3D CryoET Object IdentificationCode1
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential InformationCode1
Measure Anything: Real-time, Multi-stage Vision-based Dimensional Measurement using Segment AnythingCode1
Edge Weight Prediction For Category-Agnostic Pose EstimationCode1
OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUsCode1
OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint DetectionCode1
Center Direction Network for Grasping Point Localization on ClothsCode1
Multi-Grained Contrast for Data-Efficient Unsupervised Representation LearningCode1
Scale-Free Image Keypoints Using Differentiable Persistent HomologyCode1
CapeX: Category-Agnostic Pose Estimation from Textual Point ExplanationCode1
Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture BreedingCode1
Flowmind2Digital: The First Comprehensive Flowmind Recognition and Conversion ApproachCode1
VoxelKP: A Voxel-based Network Architecture for Human Keypoint Estimation in LiDAR DataCode1
Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D FeaturesCode1
CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage RefinementCode1
EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual LocalizationCode1
A lightweight 3D dense facial landmark estimation model from position map dataCode1
Neural Interactive Keypoint DetectionCode1
2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point CloudsCode1
Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal Image Matching on Limited DataCode1
Nonlinear optical encoding enabled by recurrent linear scatteringCode1
SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose EstimationCode1
NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point CloudCode1
Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty PropagationCode1
KGNv2: Separating Scale and Pose Prediction for Keypoint-based 6-DoF Grasp Synthesis on RGB-D inputCode1
Explicit Box Detection Unifies End-to-End Multi-Person Pose EstimationCode1
NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same ActionCode1
Dense Interspecies Face EmbeddingCode1
Show:102550
← PrevPage 1 of 7Next →

No leaderboard results yet.