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.
RBPGAN: Recurrent Back-Projection GAN for Video Super Resolution
NormNet: Scale Normalization for 6D Pose Estimation in Stacked Scenarios
FocalPose++: Focal Length and Object Pose Estimation via Render and Compare
One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion
LocaliseBot: Multi-view 3D object localisation with differentiable rendering for robot grasping
Processing and Segmentation of Human Teeth from 2D Images using Weakly Supervised Learning
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
A Lightweight Recurrent Aggregation Network for Satellite Video Super-Resolution
Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous
2D Image head pose estimation via latent space regression under occlusion settings
CESPED: a new benchmark for supervised particle pose estimation in Cryo-EM
POISE: Pose Guided Human Silhouette Extraction under Occlusions
SPADES: A Realistic Spacecraft Pose Estimation Dataset using Event Sensing
Spatial Attention-based Distribution Integration Network for Human Pose Estimation
LRM: Large Reconstruction Model for Single Image to 3D
Learning Robust Multi-Scale Representation for Neural Radiance Fields from Unposed Images
Exploring Event-based Human Pose Estimation with 3D Event Representations
An End-Cloud Computing Enabled Surveillance Video Transmission System
3D Pose Estimation of Tomato Peduncle Nodes using Deep Keypoint Detection and Point Cloud
Active Transfer Learning for Efficient Video-Specific Human Pose Estimation
UP-NeRF: Unconstrained Pose-Prior-Free Neural Radiance Fields
Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuning
TAMPAR: Visual Tampering Detection for Parcel Logistics in Postal Supply Chains
Modeling the Uncertainty with Maximum Discrepant Students for Semi-supervised 2D Pose Estimation
Generating Unbiased Pseudo-labels via a Theoretically Guaranteed Chebyshev Constraint to Unify Semi-supervised Classification and Regression
VCISR: Blind Single Image Super-Resolution with Video Compression Synthetic Data
Sim2Real Bilevel Adaptation for Object Surface Classification using Vision-Based Tactile Sensors
A Spatial-Temporal Transformer based Framework For Human Pose Assessment And Correction in Education Scenarios
HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound
HDMNet: A Hierarchical Matching Network with Double Attention for Large-scale Outdoor LiDAR Point Cloud Registration
Improving Multi-Person Pose Tracking with A Confidence Network
TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression
HSIC-based Moving WeightAveraging for Few-Shot Open-Set Object Detection
Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.