Papers with Code 아카이브

Pose Estimation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/iGame-Lab/LASOR

공식 코드

LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering

https://github.com/ianyeung/mgld-vsr

공식 코드

Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution

https://github.com/iballester/SPiKE

공식 코드

SPiKE: 3D Human Pose from Point Cloud Sequences

https://github.com/icetttb/nopesac

공식 코드

NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction

https://github.com/icitylab/posegraf

공식 코드

PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimation

https://github.com/idea-research/click-pose

공식 코드

Neural Interactive Keypoint Detection

https://github.com/idea-research/dino-x-api

공식 코드

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding

https://github.com/idea-research/dwpose

공식 코드

Effective Whole-body Pose Estimation with Two-stages Distillation

https://github.com/idea-research/ed-pose

공식 코드

Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation

https://github.com/idea-research/x-pose

공식 코드

X-Pose: Detecting Any Keypoints

https://github.com/idiap/residual_pose

공식 코드

Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation

https://github.com/idsia-robotics/proximity-quadrotor-learning

공식 코드

Vision-based Control of a Quadrotor in User Proximity: Mediated vs End-to-End Learning Approaches

https://github.com/iit-pavis/posernet

공식 코드

PoserNet: Refining Relative Camera Poses Exploiting Object Detections

https://github.com/ikea/ikea3dassemblydataset

공식 코드

IKEA Object State Dataset: A 6DoF object pose estimation dataset and benchmark for multi-state assembly objects

https://github.com/iminthemiddle/vatl4pose-wacv2024

공식 코드

Active Transfer Learning for Efficient Video-Specific Human Pose Estimation

https://github.com/imitrob/imitrob_dataset_code

공식 코드

Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators

https://github.com/imrclab/flying_adversarial_patch

공식 코드

Kidnapping Deep Learning-based Multirotors using Optimized Flying Adversarial Patches

https://github.com/inception3d/easi3r

공식 코드

Easi3R: Estimating Disentangled Motion from DUSt3R Without Training

https://github.com/indigopurple/efenet

공식 코드

EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation

https://github.com/indigopurple/tsamt

공식 코드

Cross-Camera Human Motion Transfer by Time Series Analysis

https://github.com/interactivegl/vision6d

공식 코드

Vision6D: 3D-to-2D Interactive Visualization and Annotation Tool for 6D Pose Estimation

https://github.com/ipl-uw/ZeDO-Release

공식 코드

Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation

https://github.com/irmvlab/3dunmonoflow

공식 코드

Unsupervised Learning of 3D Scene Flow from Monocular Camera

https://github.com/irmvlab/efficientlo-net

공식 코드

Efficient 3D Deep LiDAR Odometry

https://github.com/isarandi/metrabs

공식 코드

MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation

https://github.com/isarandi/metro-pose3d

공식 코드

Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation

https://github.com/isarandi/nlf

공식 코드

Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation

https://github.com/isarandi/smplfitter

공식 코드

Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation

https://github.com/isarandi/synthetic-occlusion

공식 코드

Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation

https://github.com/iscas3dv/handpose-virtualview

공식 코드

Efficient Virtual View Selection for 3D Hand Pose Estimation

https://github.com/ispgroupucl/deepsportlab

공식 코드

DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes

https://github.com/itiv-kit/dse-sparse-imu

공식 코드

Design Space Exploration on Efficient and Accurate Human Pose Estimation from Sparse IMU-Sensing

https://github.com/ivalab/kgn

공식 코드

Keypoint-GraspNet: Keypoint-based 6-DoF Grasp Generation from the Monocular RGB-D input

https://github.com/ivano-donadi/kvn

공식 코드

KVN: Keypoints Voting Network with Differentiable RANSAC for Stereo Pose Estimation

https://github.com/ivclab/Part-Aware_Measurement_for_3D_Pose_Estimation_and_Tracking

공식 코드

Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking

https://github.com/j96w/6-PACK

공식 코드

6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.