Papers with Code 아카이브

Keypoint Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 9
보존된 평가 기록: 83

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.

<span style="color:grey; opacity: 0.6">( Image credit: PifPaf: Composite Fields for Human Pose Estimation; "Learning to surf" by fotologic, license: CC-BY-2.0 )</span>

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Keypoint Detection

논문

Topology Repairing of Disconnected Pulmonary Airways and Vessels: Baselines and a Dataset

Self-supervised Interest Point Detection and Description for Fisheye and Perspective Images

Human Pose Estimation in Monocular Omnidirectional Top-View Images

SiLK -- Simple Learned Keypoints

From Saliency to DINO: Saliency-guided Vision Transformer for Few-shot Keypoint Detection

NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloud

Semantic Image Attack for Visual Model Diagnosis

Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation

ShaRPy: Shape Reconstruction and Hand Pose Estimation from RGB-D with Uncertainty

KGNv2: Separating Scale and Pose Prediction for Keypoint-based 6-DoF Grasp Synthesis on RGB-D input

PaRK-Detect: Towards Efficient Multi-Task Satellite Imagery Road Extraction via Patch-Wise Keypoints Detection

A Correct-and-Certify Approach to Self-Supervise Object Pose Estimators via Ensemble Self-Training

MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection

Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation

Vision Aided Environment Semantics Extraction and Its Application in mmWave Beam Selection

OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models

Towards High Performance One-Stage Human Pose Estimation

NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action

HandsOff: Labeled Dataset Generation With No Additional Human Annotations

Learning Markerless Robot-Depth Camera Calibration and End-Effector Pose Estimation

Learning to Detect Good Keypoints to Match Non-Rigid Objects in RGB Images

DDM-NET: End-to-end learning of keypoint feature Detection, Description and Matching for 3D localization

ViTPose++: Vision Transformer for Generic Body Pose Estimation

DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model

Images Speak in Images: A Generalist Painter for In-Context Visual Learning

BALF: Simple and Efficient Blur Aware Local Feature Detector

Real-time Detection of 2D Tool Landmarks with Synthetic Training Data

Centroid Distance Keypoint Detector for Colored Point Clouds

USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulation

Long-Lived Accurate Keypoints in Event Streams

Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hip

MetaGraspNet: A Large-Scale Benchmark Dataset for Scene-Aware Ambidextrous Bin Picking via Physics-based Metaverse Synthesis

Translating a Visual LEGO Manual to a Machine-Executable Plan

Multi-modal Retinal Image Registration Using a Keypoint-Based Vessel Structure Aligning Network

Adversarial Focal Loss: Asking Your Discriminator for Hard Examples

Human keypoint detection for close proximity human-robot interaction