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/opencv/openvino_training_extensions
공식 코드https://github.com/opengvlab/hulk
공식 코드Hulk: A Universal Knowledge Translator for Human-Centric Tasks
https://github.com/opengvlab/humanbench
공식 코드HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
https://github.com/opengvlab/unihcp
공식 코드https://github.com/opengvlab/visionllm
공식 코드https://github.com/opentrack/neuralnet-tracker-traincode
공식 코드https://github.com/openxrlab/xrfeitoria
공식 코드https://github.com/openxrlab/xrlocalization
공식 코드Improving Feature-based Visual Localization by Geometry-Aided Matching
https://github.com/opipari/clearpose
공식 코드ClearPose: Large-scale Transparent Object Dataset and Benchmark
https://github.com/oppo-us-research/PoP-Net
공식 코드PoP-Net: Pose over Parts Network for Multi-Person 3D Pose Estimation from a Depth Image
https://github.com/orhir/EdgeCape
공식 코드Edge Weight Prediction For Category-Agnostic Pose Estimation
https://github.com/orhir/PoseAnything
공식 코드A Graph-Based Approach for Category-Agnostic Pose Estimation
https://github.com/orhir/stg-nf
공식 코드https://github.com/ostadabbas/Infant-Pose-Estimation
공식 코드Invariant Representation Learning for Infant Pose Estimation with Small Data
https://github.com/ostadabbas/SLP-Dataset-and-Code
공식 코드https://github.com/ostadabbas/SPAC-Net-Synthetic-Pose-aware-Animal-ControlNet
공식 코드SPAC-Net: Synthetic Pose-aware Animal ControlNet for Enhanced Pose Estimation
https://github.com/ostadabbas/ScanAvaGenerationToolkit
공식 코드A Semi-Supervised Data Augmentation Approach using 3D Graphical Engines
https://github.com/ostadabbas/adaptedhumanpose
공식 코드Adapted Human Pose: Monocular 3D Human Pose Estimation with Zero Real 3D Pose Data
https://github.com/ostadabbas/hw-hup
공식 코드https://github.com/ostadabbas/infant-postural-symmetry
공식 코드Computer Vision to the Rescue: Infant Postural Symmetry Estimation from Incongruent Annotations
https://github.com/ostadabbas/infant-upper-body-postural-symmetry
공식 코드Automatic Assessment of Infant Face and Upper-Body Symmetry as Early Signs of Torticollis
https://github.com/ostadabbas/nns-detection-and-segmentation
공식 코드https://github.com/ostadabbas/prior-aware-synthetic-data-generation-pasyn-
공식 코드Prior-Aware Synthetic Data to the Rescue: Animal Pose Estimation with Very Limited Real Data
https://github.com/ostadabbas/tepose
공식 코드Live Stream Temporally Embedded 3D Human Body Pose and Shape Estimation
https://github.com/otaheri/GRAB
공식 코드https://github.com/otl-artorg/instrument-pose
공식 코드Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery
https://github.com/owensun2004/Manual2Skill
공식 코드https://github.com/oxpig/cesped
공식 코드CESPED: a new benchmark for supervised particle pose estimation in Cryo-EM
https://github.com/paTRICK-swk/Pose3D-RIE
공식 코드Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation
https://github.com/padeler/pe-former
공식 코드https://github.com/pandorgan/apt
공식 코드APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking
https://github.com/pandorgan/apt-36k
공식 코드APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking
https://github.com/parkjaewoo0611/dprost
공식 코드DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimation
https://github.com/paroj/ycbev
공식 코드YCB-Ev 1.1: Event-vision dataset for 6DoF object pose estimation
https://github.com/parskatt/dad
공식 코드DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.