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.
X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
RTSR: A Real-Time Super-Resolution Model for AV1 Compressed Content
Developing Normative Gait Cycle Parameters for Clinical Analysis Using Human Pose Estimation
MTFusion: Reconstructing Any 3D Object from Single Image Using Multi-word Textual Inversion
GLOVER: Generalizable Open-Vocabulary Affordance Reasoning for Task-Oriented Grasping
IoT-Based 3D Pose Estimation and Motion Optimization for Athletes: Application of C3D and OpenPose
VioPose: Violin Performance 4D Pose Estimation by Hierarchical Audiovisual Inference
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
Direct and Explicit 3D Generation from a Single Image
ARM: Appearance Reconstruction Model for Relightable 3D Generation
USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting
SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstruction
Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting
Generalized Pose Space Embeddings for Training In-the-Wild using Anaylis-by-Synthesis
ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening
Towards Seamless Integration of Magnetic Tracking into Fluoroscopy-guided Interventions
CameraHMR: Aligning People with Perspective
GTA-Net: An IoT-Integrated 3D Human Pose Estimation System for Real-Time Adolescent Sports Posture Correction
360-Degree Video Super Resolution and Quality Enhancement Challenge: Methods and Results
CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models
AI-Driven Stylization of 3D Environments
Tightly-Coupled, Speed-aided Monocular Visual-Inertial Localization in Topological Map
DeepArUco++: Improved detection of square fiducial markers in challenging lighting conditions
Poze: Sports Technique Feedback under Data Constraints
Acoustic-based 3D Human Pose Estimation Robust to Human Position
Pose2Trajectory: Using Transformers on Body Pose to Predict Tennis Player's Trajectory
Social EgoMesh Estimation
Controlling Human Shape and Pose in Text-to-Image Diffusion Models via Domain Adaptation
Estimation of Psychosocial Work Environment Exposures Through Video Object Detection. Proof of Concept Using CCTV Footage
GS2Pose: Two-stage 6D Object Pose Estimation Guided by Gaussian Splatting
HFGaussian: Learning Generalizable Gaussian Human with Integrated Human Features
Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data
KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension
Silver medal Solution for Image Matching Challenge 2024
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.