https://github.com/liuyuan-pal/syncdreamer
공식 코드SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
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.
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
Modeling Uncertain Feature Representation for Domain Generalization
CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction
ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision
RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution
3D Human Pose Estimation in RGBD Images for Robotic Task Learning
DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model
GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting
LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation
RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation
Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
A Single Frame and Multi-Frame Joint Network for 360-degree Panorama Video Super-Resolution
A Single Frame and Multi-Frame Joint Network for 360-degree Panorama Video Super-Resolution
Unsupervised Human Pose Estimation through Transforming Shape Templates
Why Sample Space Matters: Keyframe Sampling Optimization for LiDAR-based Place Recognition
Learning Structure-from-Motion with Graph Attention Networks
ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search
Pose for Everything: Towards Category-Agnostic Pose Estimation
HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation
Topology Repairing of Disconnected Pulmonary Airways and Vessels: Baselines and a Dataset
Let's take a Walk on Superpixels Graphs: Deformable Linear Objects Segmentation and Model Estimation
Let's take a Walk on Superpixels Graphs: Deformable Linear Objects Segmentation and Model Estimation
Effective Deployment of CNNs for 3DoF Pose Estimation and Grasping in Industrial Settings
EKFPnP: Extended Kalman Filter for Camera Pose Estimation in a Sequence of Images
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.