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.
PolyFit: A Peg-in-hole Assembly Framework for Unseen Polygon Shapes via Sim-to-real Adaptation
A Unified Simulation Framework for Visual and Behavioral Fidelity in Crowd Analysis
Multi-View Person Matching and 3D Pose Estimation with Arbitrary Uncalibrated Camera Networks
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
Disentangled Interaction Representation for One-Stage Human-Object Interaction Detection
SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM
iMatching: Imperative Correspondence Learning
CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy
S2P3: Self-Supervised Polarimetric Pose Prediction
Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors
Learning Unorthogonalized Matrices for Rotation Estimation
Global Localization: Utilizing Relative Spatio-Temporal Geometric Constraints from Adjacent and Distant Cameras
Tracking Object Positions in Reinforcement Learning: A Metric for Keypoint Detection (extended version)
Open-vocabulary object 6D pose estimation
Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution
FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models
Hypergraph Contrastive Learning for Drug Trafficking Community Detection
Utilizing Radiomic Feature Analysis For Automated MRI Keypoint Detection: Enhancing Graph Applications
Pose Estimation and Tracking for ASIST
FoundPose: Unseen Object Pose Estimation with Foundation Features
ChatPose: Chatting about 3D Human Pose
Enhancing Ligand Pose Sampling for Molecular Docking
DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation
W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration
PViT-6D: Overclocking Vision Transformers for 6D Pose Estimation with Confidence-Level Prediction and Pose Tokens
Cinematic Behavior Transfer via NeRF-based Differentiable Filming
A Graph-Based Approach for Category-Agnostic Pose Estimation
A Stochastic-Geometrical Framework for Object Pose Estimation based on Mixture Models Avoiding the Correspondence Problem
Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features
Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement
HandyPriors: Physically Consistent Perception of Hand-Object Interactions with Differentiable Priors
DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffuser
UGG: Unified Generative Grasping
HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion
Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.