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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Towards Unconstrained 2D Pose Estimation of the Human Spine
Setup-Invariant Augmented Reality for Teaching by Demonstration with Surgical Robots
GraspClutter6D: A Large-scale Real-world Dataset for Robust Perception and Grasping in Cluttered Scenes
Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation
Objaverse++: Curated 3D Object Dataset with Quality Annotations
DLTPose: 6DoF Pose Estimation From Accurate Dense Surface Point Estimates
POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction
An Empirical Study of GPT-4o Image Generation Capabilities
PromptHMR: Promptable Human Mesh Recovery
Learning Affine Correspondences by Integrating Geometric Constraints
Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video
Robust Human Registration with Body Part Segmentation on Noisy Point Clouds
PicoPose: Progressive Pixel-to-Pixel Correspondence Learning for Novel Object Pose Estimation
BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimation
Cooperative Inference for Real-Time 3D Human Pose Estimation in Multi-Device Edge Networks
ForestVO: Enhancing Visual Odometry in Forest Environments through ForestGlue
Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation
A Geometric Approach For Pose and Velocity Estimation Using IMU and Inertial/Body-Frame Measurements
LiM-Loc: Visual Localization with Dense and Accurate 3D Reference Maps Directly Corresponding 2D Keypoints to 3D LiDAR Point Clouds
Easi3R: Estimating Disentangled Motion from DUSt3R Without Training
SuperEvent: Cross-Modal Learning of Event-based Keypoint Detection
HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation
PhysPose: Refining 6D Object Poses with Physical Constraints
FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video
Incorporating GNSS Information with LIDAR-Inertial Odometry for Accurate Land-Vehicle Localization
GCRayDiffusion: Pose-Free Surface Reconstruction via Geometric Consistent Ray Diffusion
ForcePose: A Deep Learning Approach for Force Calculation Based on Action Recognition Using MediaPipe Pose Estimation Combined with Object Detection
Grasping a Handful: Sequential Multi-Object Dexterous Grasp Generation
Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation
STAMICS: Splat, Track And Map with Integrated Consistency and Semantics for Dense RGB-D SLAM
RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a Millisecond
OccRobNet : Occlusion Robust Network for Accurate 3D Interacting Hand-Object Pose Estimation
3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models
Reconstructing Humans with a Biomechanically Accurate Skeleton
Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.