https://github.com/ianyeung/mgld-vsr
공식 코드Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution
PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimation
Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation
Vision-based Control of a Quadrotor in User Proximity: Mediated vs End-to-End Learning Approaches
EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation
Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation
MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation
Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation
Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation
Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation
KGNv2: Separating Scale and Pose Prediction for Keypoint-based 6-DoF Grasp Synthesis on RGB-D input
Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking
A Deep Learning Ensemble Framework for Off-Nadir Geocentric Pose Prediction
PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation
HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization
Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo
Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation
LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF
Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal Transformer
Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
Recurrent Video Restoration Transformer with Guided Deformable Attention
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.