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.
Reconstructing Groups of People with Hypergraph Relational Reasoning
Spatio-temporal MLP-graph network for 3D human pose estimation
PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point Clouds
DF-3DFace: One-to-Many Speech Synchronized 3D Face Animation with Diffusion
PoseGraphNet++: Enriching 3D Human Pose with Orientation Estimation
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video
3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation
Denoising Diffusion for 3D Hand Pose Estimation from Images
PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation
SimDA: Simple Diffusion Adapter for Efficient Video Generation
Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modeling
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere
Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction
Double-chain Constraints for 3D Human Pose Estimation in Images and Videos
Speech-Driven 3D Face Animation with Composite and Regional Facial Movements
Improved Cryo-EM Pose Estimation and 3D Classification through Latent-Space Disentanglement
Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes
Iterative Graph Filtering Network for 3D Human Pose Estimation
Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Driving
Learning Snippet-to-Motion Progression for Skeleton-based Human Motion Prediction
CycMuNet+: Cycle-Projected Mutual Learning for Spatial-Temporal Video Super-Resolution
SimCol3D -- 3D Reconstruction during Colonoscopy Challenge
ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting
MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution
GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video
Equivariant Single View Pose Prediction Via Induced and Restricted Representations
Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation
RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution
Spatio-Temporal Perception-Distortion Trade-off in Learned Video SR
ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning
Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view
Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
Representation learning of vertex heatmaps for 3D human mesh reconstruction from multi-view images
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.