https://github.com/axelBarroso/Key.Net
공식 코드Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters
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>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/baaivision/painter
공식 코드Images Speak in Images: A Generalist Painter for In-Context Visual Learning
https://github.com/benbillot/spatial_regularisation
공식 코드Spatial regularisation for improved accuracy and interpretability in keypoint-based registration
https://github.com/bgu-cs-vil/timepoint
공식 코드TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
https://github.com/bluedream1121/REKD
공식 코드Self-Supervised Equivariant Learning for Oriented Keypoint Detection
https://github.com/boschresearch/symfm6d
공식 코드SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose Estimation
https://github.com/cai-jianfeng/flowmind2digital
공식 코드Flowmind2Digital: The First Comprehensive Flowmind Recognition and Conversion Approach
https://github.com/caiyuanhao1998/RSN
공식 코드Learning Delicate Local Representations for Multi-Person Pose Estimation
https://github.com/carluerjb/3d_sift_cuda
공식 코드https://github.com/chaimi2013/CCM
공식 코드https://github.com/chakkritte/eeea-net
공식 코드EEEA-Net: An Early Exit Evolutionary Neural Architecture Search
https://github.com/chen-xin-94/ocdet
공식 코드OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs
https://github.com/chenyilun95/tf-cpn
공식 코드https://github.com/comedialkb/learning_with_passive_optical_nonlinear_mapping
공식 코드Nonlinear optical encoding enabled by recurrent linear scattering
https://github.com/data-science-in-mechanical-engineering/sae-rl
공식 코드https://github.com/dongzhou-1996/gknet
공식 코드GKNet: Graph-based Keypoints Network for Monocular Pose Estimation of Non-cooperative Spacecraft
https://github.com/duncanzauss/keypoint_communities
공식 코드https://github.com/dxbdxx/bpfnet
공식 코드BPFNet: A Unified Framework for Bimodal Palmprint Alignment and Fusion
https://github.com/ethnhe/PVN3D
공식 코드PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
https://github.com/ethz-asl/3d3l
공식 코드3D3L: Deep Learned 3D Keypoint Detection and Description for LiDARs
https://github.com/facebookresearch/silk
공식 코드https://github.com/facebookresearch/video-nonlocal-net
공식 코드https://github.com/fiy2w/treatment-aware-longitudinal-registration
공식 코드https://github.com/gbarbarani/MorseDet
공식 코드Scale-Free Image Keypoints Using Differentiable Persistent Homology
https://github.com/giddyyupp/coco-minitrain
공식 코드HoughNet: Integrating near and long-range evidence for visual detection
https://github.com/google-research/pix2seq
공식 코드https://github.com/haksorus/gsplatloc
공식 코드https://github.com/haoyu94/coarse-to-fine-correspondences
공식 코드CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration
https://github.com/hellojialee/Improved-Body-Parts
공식 코드Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation
https://github.com/hellojialee/OffsetGuided
공식 코드Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation
https://github.com/idea-research/click-pose
공식 코드https://github.com/idea-research/ed-pose
공식 코드Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation
https://github.com/idea-research/x-pose
공식 코드https://github.com/ivalab/kgn
공식 코드KGNv2: Separating Scale and Pose Prediction for Keypoint-based 6-DoF Grasp Synthesis on RGB-D input
https://github.com/jhacsonmeza/MarkerPose
공식 코드MarkerPose: Robust Real-time Planar Target Tracking for Accurate Stereo Pose Estimation
https://github.com/jiahaoLjh/PoseGrouping
공식 코드Learning Spatial Context with Graph Neural Network for Multi-Person Pose Grouping
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.