Papers with Code 아카이브
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/moberweger/deep-prior-pp
공식 코드DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation
https://github.com/moberweger/semi-auto-anno
공식 코드Efficiently Creating 3D Training Data for Fine Hand Pose Estimation
https://github.com/mohamedhassanmus/POSA
공식 코드https://github.com/mohomran/neural_body_fitting
공식 코드Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation
https://github.com/mohsij/space-event-rgb-fusion
공식 코드Event-RGB Fusion for Spacecraft Pose Estimation Under Harsh Lighting
https://github.com/mookerr/varges
공식 코드VarGes: Improving Variation in Co-Speech 3D Gesture Generation via StyleCLIPS
https://github.com/moranli-aca/LearnableGroups-Hand
공식 코드https://github.com/mosamdabhi/3dlfm
공식 코드https://github.com/mosamdabhi/mbw
공식 코드https://github.com/mosamdabhi/mbw-data
공식 코드https://github.com/motionmlp/motionmixer
공식 코드https://github.com/mperneel/Kantool
공식 코드Consistent multi-animal pose estimation in cattle using dynamic Kalman filter based tracking
https://github.com/mpuu00001/robustness-evaluation-in-hand-pose-estimation
공식 코드Robustness Evaluation in Hand Pose Estimation Models using Metamorphic Testing
https://github.com/mrezaei92/TriHorn-Net
공식 코드TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation
https://github.com/msbrpp/MSBR
공식 코드https://github.com/msu-video-group/erqa
공식 코드ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution
https://github.com/msu-video-group/srdm
공식 코드Combining Contrastive and Supervised Learning for Video Super-Resolution Detection
https://github.com/muelea/shapy
공식 코드Accurate 3D Body Shape Regression using Metric and Semantic Attributes
https://github.com/multimodallearning/da-3dhpe-anatomy
공식 코드Anatomy-guided domain adaptation for 3D in-bed human pose estimation
https://github.com/mvig-sjtu/artiboost
공식 코드ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
https://github.com/n-nejatishahidin/pose_from_mid-level
공식 코드Object Pose Estimation using Mid-level Visual Representations
https://github.com/naibaf7/pose_estimation
공식 코드Robust Large-Scale Localization in 3D Point Clouds Revisited
https://github.com/nankingjing/PoseMamba
공식 코드https://github.com/natanielruiz/deep-head-pose
공식 코드https://github.com/natanielruiz/dockerface
공식 코드Dockerface: an Easy to Install and Use Faster R-CNN Face Detector in a Docker Container
https://github.com/nationalgailab/hot
공식 코드Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
https://github.com/naver/croco
공식 코드CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion
https://github.com/naver/dust3r
공식 코드https://github.com/naver/kapture
공식 코드Robust Image Retrieval-based Visual Localization using Kapture
https://github.com/naver/kapture-localization
공식 코드Robust Image Retrieval-based Visual Localization using Kapture
https://github.com/naver/multi-hmr
공식 코드Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot
https://github.com/naver/posebert
공식 코드PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling
https://github.com/nerminsamet/HPRNet
공식 코드HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation
https://github.com/nerminsamet/houghnet
공식 코드HoughNet: Integrating near and long-range evidence for visual detection
https://github.com/nesc-iv/sage-icp
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.