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.
DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models
LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models
Learning Visual Generative Priors without Text
Attention-Enhanced Lightweight Hourglass Network for Human Pose Estimation
ZeroKey: Point-Level Reasoning and Zero-Shot 3D Keypoint Detection from Large Language Models
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential Information
Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergy
Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds
CCS: Continuous Learning for Customized Incremental Wireless Sensing Services
Targeted Hard Sample Synthesis Based on Estimated Pose and Occlusion Error for Improved Object Pose Estimation
DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction
ProPLIKS: Probablistic 3D human body pose estimation
An indoor DSO-based ceiling-vision odometry system for indoor industrial environments
Measure Anything: Real-time, Multi-stage Vision-based Dimensional Measurement using Segment Anything
A Bidirectional Siamese Recurrent Neural Network for Accurate Gait Recognition Using Body Landmarks
NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images
Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis
CLERF: Contrastive LEaRning for Full Range Head Pose Estimation
Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images
ProbPose: A Probabilistic Approach to 2D Human Pose Estimation
EgoCast: Forecasting Egocentric Human Pose in the Wild
CRISP: Object Pose and Shape Estimation with Test-Time Adaptation
Cross-Modal Visual Relocalization in Prior LiDAR Maps Utilizing Intensity Textures
MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detection
SF-Loc: A Visual Mapping and Geo-Localization System based on Sparse Visual Structure Frames
HandOS: 3D Hand Reconstruction in One Stage
6DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting
World-consistent Video Diffusion with Explicit 3D Modeling
emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation
FlashSLAM: Accelerated RGB-D SLAM for Real-Time 3D Scene Reconstruction with Gaussian Splatting
Particle-based 6D Object Pose Estimation from Point Clouds using Diffusion Models
ESCAPE: Equivariant Shape Completion via Anchor Point Encoding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.