Papers with Code 아카이브
3D Human Pose Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 9
- 평가표
- 25
- 보존된 평가 기록
- 447
3D Human Pose Estimation is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modeling
LPFormer: LiDAR Pose Estimation Transformer with Multi-Task Network
SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces
EVOPOSE: A Recursive Transformer For 3D Human Pose Estimation With Kinematic Structure Priors
Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers
Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception
Motion-DVAE: Unsupervised learning for fast human motion denoising
ATT3D: Amortized Text-to-3D Object Synthesis
TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments
Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation
Humans in 4D: Reconstructing and Tracking Humans with Transformers
Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training
ZeroAvatar: Zero-shot 3D Avatar Generation from a Single Image
NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-World Video Super-Resolution
EgoVSR: Towards High-Quality Egocentric Video Super-Resolution
XFormer: Fast and Accurate Monocular 3D Body Capture
NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation
Can SAM Boost Video Super-Resolution?
HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation
Regular Splitting Graph Network for 3D Human Pose Estimation
RelPose++: Recovering 6D Poses from Sparse-view Observations
Expanding Synthetic Real-World Degradations for Blind Video Super Resolution
Enhancing Video Super-Resolution via Implicit Resampling-based Alignment
TAPE: Temporal Attention-based Probabilistic human pose and shape Estimation
Interweaved Graph and Attention Network for 3D Human Pose Estimation
Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation
Sampling is Matter: Point-guided 3D Human Mesh Reconstruction
Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion
Human Pose Estimation in Monocular Omnidirectional Top-View Images
Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments
Shape of You: Precise 3D shape estimations for diverse body types
Meta-Auxiliary Learning for Adaptive Human Pose Prediction
HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery
Multi-Graph Convolution Network for Pose Forecasting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.