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.
Assistive Image Annotation Systems with Deep Learning and Natural Language Capabilities: A Review
Human Modelling and Pose Estimation Overview
Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Reference
Automatic infant 2D pose estimation from videos: comparing seven deep neural network methods
Improving Generative Adversarial Networks for Video Super-Resolution
High-resolution open-vocabulary object 6D pose estimation
ID-Sculpt: ID-aware 3D Head Generation from Single In-the-wild Portrait Image
Breaking the Frame: Visual Place Recognition by Overlap Prediction
Investigating the impact of 2D gesture representation on co-speech gesture generation
Efficient Human Pose Estimation: Leveraging Advanced Techniques with MediaPipe
PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions
Benchmarking Monocular 3D Dog Pose Estimation Using In-The-Wild Motion Capture Data
EvTexture: Event-driven Texture Enhancement for Video Super-Resolution
An Efficient yet High-Performance Method for Precise Radar-Based Imaging of Human Hand Poses
MVSBoost: An Efficient Point Cloud-based 3D Reconstruction
CNN Based Flank Predictor for Quadruped Animal Species
NeRF-Feat: 6D Object Pose Estimation using Feature Rendering
Head Pose Estimation and 3D Neural Surface Reconstruction via Monocular Camera in situ for Navigation and Safe Insertion into Natural Openings
AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulation
SeamPose: Repurposing Seams as Capacitive Sensors in a Shirt for Upper-Body Pose Tracking
Domain Generalization for In-Orbit 6D Pose Estimation
Matching Query Image Against Selected NeRF Feature for Efficient and Scalable Localization
CryoSPIN: Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inference
MMVR: Millimeter-wave Multi-View Radar Dataset and Benchmark for Indoor Perception
OpenCapBench: A Benchmark to Bridge Pose Estimation and Biomechanics
MeshPose: Unifying DensePose and 3D Body Mesh reconstruction
The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences
Galibr: Targetless LiDAR-Camera Extrinsic Calibration Method via Ground Plane Initialization
Deep Transformer Network for Monocular Pose Estimation of Ship-Based UAV
ImageNet3D: Towards General-Purpose Object-Level 3D Understanding
From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers
IFTD: Image Feature Triangle Descriptor for Loop Detection in Driving Scenes
Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization
VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks
SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.