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.
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers
KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
NeuriCam: Key-Frame Video Super-Resolution and Colorization for IoT Cameras
Live Stream Temporally Embedded 3D Human Body Pose and Shape Estimation
Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection
Dynamic Graph Reasoning for Multi-person 3D Pose Estimation
QuickPose: Real-time Multi-view Multi-person Pose Estimation in Crowded Scenes
Towards Interpretable Video Super-Resolution via Alternating Optimization
VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data
DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose Estimation
Computer Vision to the Rescue: Infant Postural Symmetry Estimation from Incongruent Annotations
Rethinking Alignment in Video Super-Resolution Transformers
Geometry-Aware Reference Synthesis for Multi-View Image Super-Resolution
Boosting Video Super Resolution with Patch-Based Temporal Redundancy Optimization
Enhancing Space-time Video Super-resolution via Spatial-temporal Feature Interaction
Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
You Only Align Once: Bidirectional Interaction for Spatial-Temporal Video Super-Resolution
PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images
Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior
Collaborative Neural Rendering using Anime Character Sheets
Learning to Estimate External Forces of Human Motion in Video
Learning-based Monocular 3D Reconstruction of Birds: A Contemporary Survey
PoseGU: 3D Human Pose Estimation with Novel Human Pose Generator and Unbiased Learning
Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation
Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution
BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation
Capturing and Inferring Dense Full-Body Human-Scene Contact
Embodied Scene-aware Human Pose Estimation
Structured Sparsity Learning for Efficient Video Super-Resolution
Accurate 3D Body Shape Regression using Metric and Semantic Attributes
AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos
GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation
Efficient Human Pose Estimation via 3D Event Point Cloud
VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.