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.
Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset
HydraScreen: A Generalizable Structure-Based Deep Learning Approach to Drug Discovery
A Real-Time Multi-Task Learning System for Joint Detection of Face, Facial Landmark and Head Pose
Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views
ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers
ORTexME: Occlusion-Robust Human Shape and Pose via Temporal Average Texture and Mesh Encoding
FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion
Understanding Pose and Appearance Disentanglement in 3D Human Pose Estimation
RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery
GloPro: Globally-Consistent Uncertainty-Aware 3D Human Pose Estimation & Tracking in the Wild
MAGIC-TBR: Multiview Attention Fusion for Transformer-based Bodily Behavior Recognition in Group Settings
Sparse and Privacy-enhanced Representation for Human Pose Estimation
RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy
Application-driven Validation of Posteriors in Inverse Problems
Hierarchical Attention and Graph Neural Networks: Toward Drift-Free Pose Estimation
RenderIH: A Large-scale Synthetic Dataset for 3D Interacting Hand Pose Estimation
DynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fields
Staged Contact-Aware Global Human Motion Forecasting
Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM
YCB-Ev 1.1: Event-vision dataset for 6DoF object pose estimation
Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild
Unleashing the Power of Depth and Pose Estimation Neural Networks by Designing Compatible Endoscopic Images
EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization
Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimation
TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting
LInKs "Lifting Independent Keypoints" -- Partial Pose Lifting for Occlusion Handling with Improved Accuracy in 2D-3D Human Pose Estimation
ViHOPE: Visuotactile In-Hand Object 6D Pose Estimation with Shape Completion
FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions
Mirror-Aware Neural Humans
Probabilistic Triangulation for Uncalibrated Multi-View 3D Human Pose Estimation
AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations
Robot Localization and Mapping Final Report -- Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
AnthroNet: Conditional Generation of Humans via Anthropometrics
ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.