Pose Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 17
- 평가표
- 31
- 보존된 평가 기록
- 235
Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.
A common benchmark for this task is MPII Human Pose
<span style="color:grey; opacity: 0.6">( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ayoolaolafenwa/PixelLib
https://github.com/azad96/cosypose-custom
CosyPose: Consistent multi-view multi-object 6D pose estimation
https://github.com/azizanlab/unlimitd
https://github.com/baizhenmao95/2019-ZTE-Algorithm-Competition
DAC: Data-free Automatic Acceleration of Convolutional Networks
https://github.com/balala8/FastViT_pytorch
FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
https://github.com/baodi23/hourglass-facekeypoints-detection
https://github.com/baoshengyu/deep-high-resolution-net.pytorch
Deep High-Resolution Representation Learning for Human Pose Estimation
https://github.com/bastianwandt/RepNet
https://github.com/bastianwandt/elepose
https://github.com/bayuudachi/Real-esr-gan
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
https://github.com/bazilas/matconvnet-deepReg
https://github.com/bearpaw/pose-attention
https://github.com/bearpaw/pytorch-pose
https://github.com/beassssry/U
https://github.com/behnoudshafizadeh/ESPCN-SuperResolution-Tensorflow
https://github.com/benjs/hourglass_networks
https://github.com/bespontaneous/ffn
UniFormer: Unifying Convolution and Self-attention for Visual Recognition
https://github.com/bespontaneous/mca-pytorch
UniFormer: Unifying Convolution and Self-attention for Visual Recognition
https://github.com/bethgelab/siamese-mask-rcnn
https://github.com/bharat-b7/IPNet
Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction
https://github.com/bharat-b7/MultiGarmentNetwork
https://github.com/blake58/openpose
https://github.com/blueardour/AdelaiDet
https://github.com/bluedream1121/Key.Net_PyTorch
Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters
https://github.com/bmartacho/BAPose
BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations
https://github.com/bnestor/second-hand-rl
https://github.com/bo-zhang-cs/CACNet-Pytorch
A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image
https://github.com/boom85423/Cartoon-style-Stickers-Generator
https://github.com/bordac6/PNNPPV_project
https://github.com/boreshkinai/smpl-ik
SMPL-IK: Learned Morphology-Aware Inverse Kinematics for AI Driven Artistic Workflows
https://github.com/borglab/gtsfm
SuperGlue: Learning Feature Matching with Graph Neural Networks
https://github.com/boschresearch/numerics_independent_neural_odes
https://github.com/boukhayma/3dhand
https://github.com/bouracha/Gen_Motion
Learning Trajectory Dependencies for Human Motion Prediction
https://github.com/bouracha/OoDMotion
Learning Trajectory Dependencies for Human Motion Prediction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.