https://github.com/LongguangWang/SOF-VSR
공식 코드Deep Video Super-Resolution using HR Optical Flow Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Deep Video Super-Resolution using HR Optical Flow Estimation
Learning for Video Super-Resolution through HR Optical Flow Estimation
HandTailor: Towards High-Precision Monocular 3D Hand Recovery
AutoSNAP: Automatically Learning Neural Architectures for Instrument Pose Estimation
One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers
Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Training
MONET: Multiview Semi-supervised Keypoint Detection via Epipolar Divergence
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
REF-VLM: Triplet-Based Referring Paradigm for Unified Visual Decoding
Deep Alignment Network: A convolutional neural network for robust face alignment
HoloFace: Augmenting Human-to-Human Interactions on HoloLens
Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework
Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance
Measuring Physical Plausibility of 3D Human Poses Using Physics Simulation
Temporally Guided Articulated Hand Pose Tracking in Surgical Videos
Deep High-Resolution Representation Learning for Human Pose Estimation
Learning Pyramid-structured Long-range Dependencies for 3D Human Pose Estimation
Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
ProbPose: A Probabilistic Approach to 2D Human Pose Estimation
Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data
Resolving 3D Human Pose Ambiguities with 3D Scene Constraints
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement
SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation
BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.