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.
Multi Positive Contrastive Learning with Pose-Consistent Generated Images
SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation
SemGrasp: Semantic Grasp Generation via Language Aligned Discretization
The More You See in 2D, the More You Perceive in 3D
Semi-Supervised Unconstrained Head Pose Estimation in the Wild
Translation-based Video-to-Video Synthesis
Sketch3D: Style-Consistent Guidance for Sketch-to-3D Generation
SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation
3D Congealing: 3D-Aware Image Alignment in the Wild
Marrying NeRF with Feature Matching for One-step Pose Estimation
FlexiDreamer: Single Image-to-3D Generation with FlexiCubes
KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation
OmniLocalRF: Omnidirectional Local Radiance Fields from Dynamic Videos
Video-Based Human Pose Regression via Decoupled Space-Time Aggregation
A Unified Framework for Human-centric Point Cloud Video Understanding
Latent Embedding Clustering for Occlusion Robust Head Pose Estimation
FetalDiffusion: Pose-Controllable 3D Fetal MRI Synthesis with Conditional Diffusion Model
Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation
Efficient Heatmap-Guided 6-Dof Grasp Detection in Cluttered Scenes
HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions
Garment3DGen: 3D Garment Stylization and Texture Generation
TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos
GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstruction
A Survey on 3D Egocentric Human Pose Estimation
AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation
Mathematical Foundation and Corrections for Full Range Head Pose Estimation
Sketch2Prototype: Rapid Conceptual Design Exploration and Prototyping with Generative AI
ASDF: Assembly State Detection Utilizing Late Fusion by Integrating 6D Pose Estimation
A Geometric Perspective on Fusing Gaussian Distributions on Lie Groups
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution
Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos
Diffusion Model is a Good Pose Estimator from 3D RF-Vision
SUP-NeRF: A Streamlined Unification of Pose Estimation and NeRF for Monocular 3D Object Reconstruction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.