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.
ViewSynth: Learning Local Features from Depth using View Synthesis
DirectPose: Direct End-to-End Multi-Person Pose Estimation
PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
Human Keypoint Detection by Progressive Context Refinement
Distribution-Aware Coordinate Representation for Human Pose Estimation
kPAM-SC: Generalizable Manipulation Planning using KeyPoint Affordance and Shape Completion
Pose Neural Fabrics Search
Computer-Aided Automated Detection of Gene-Controlled Social Actions of Drosophila
Learning Enhanced Resolution-wise features for Human Pose Estimation
A Comparison of CNN and Classic Features for Image Retrieval
Single-Stage Multi-Person Pose Machines
GLAMpoints: Greedily Learned Accurate Match points
Self-supervised Learning of Interpretable Keypoints from Unlabelled Videos
R2D2: Repeatable and Reliable Detector and Descriptor
RF-Net: An End-to-End Image Matching Network based on Receptive Field
Monocular 3D Object Detection via Geometric Reasoning on Keypoints
Objects as Points
Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters
KPTransfer: improved performance and faster convergence from keypoint subset-wise domain transfer in human pose estimation
PifPaf: Composite Fields for Human Pose Estimation
Deep High-Resolution Representation Learning for Human Pose Estimation
Rethinking on Multi-Stage Networks for Human Pose Estimation
Slimmable Neural Networks
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
PoseFix: Model-agnostic General Human Pose Refinement Network
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
Multiview Supervision By Registration
Blur-Countering Keypoint Detection via Eigenvalue Asymmetry
Multi-Scale Supervised Network for Human Pose Estimation
MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network
MONET: Multiview Semi-supervised Keypoint Detection via Epipolar Divergence
Learning to Refine Human Pose Estimation
Simple Baselines for Human Pose Estimation and Tracking
Towards Deep Learning based Hand Keypoints Detection for Rapid Sequential Movements from RGB Images
Pose2Seg: Detection Free Human Instance Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.