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.
RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution
SignX: The Foundation Model for Sign Recognition
SmallGS: Gaussian Splatting-based Camera Pose Estimation for Small-Baseline Videos
Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimation
Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs
Vision6D: 3D-to-2D Interactive Visualization and Annotation Tool for 6D Pose Estimation
Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction
Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction
Imitation Learning with Precisely Labeled Human Demonstrations
Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms
TwoSquared: 4D Generation from 2D Image Pairs
Event-Enhanced Blurry Video Super-Resolution
ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos
ViTa-Zero: Zero-shot Visuotactile Object 6D Pose Estimation
An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World
CoMotion: Concurrent Multi-person 3D Motion
Regist3R: Incremental Registration with Stereo Foundation Model
Diffusion Based Robust LiDAR Place Recognition
MobilePoser: Real-Time Full-Body Pose Estimation and 3D Human Translation from IMUs in Mobile Consumer Devices
ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping
UKDM: Underwater keypoint detection and matching using underwater image enhancement techniques
DMAGaze: Gaze Estimation Based on Feature Disentanglement and Multi-Scale Attention
CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image
TT3D: Table Tennis 3D Reconstruction
Differentially Private 2D Human Pose Estimation
Benchmarking 3D Human Pose Estimation Models Under Occlusions
MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model
Art3D: Training-Free 3D Generation from Flat-Colored Illustration
EasyREG: Easy Depth-Based Markerless Registration and Tracking using Augmented Reality Device for Surgical Guidance
A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds
Multi-person Physics-based Pose Estimation for Combat Sports
Stereophotoclinometry Revisited
Hardware, Algorithms, and Applications of the Neuromorphic Vision Sensor: a Review
MBE-ARI: A Multimodal Dataset Mapping Bi-directional Engagement in Animal-Robot Interaction
The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.