https://github.com/thusiyuan/cooperative_scene_parsing
공식 코드Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose 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.
Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation
Object Pose Estimation via the Aggregation of Diffusion Features
Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects
Semi-supervised Human Pose Estimation in Art-historical Images
Convex Hull-based Algebraic Constraint for Visual Quadric SLAM
Automatic Analysis of Human Body Representations in Western Art
MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation
Learning Keypoints from Synthetic Data for Robotic Cloth Folding
Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration
HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media
CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data
Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade
milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing
SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gap
Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gap
Simple Multi-Resolution Representation Learning for Human Pose Estimation
Learning to Produce Semi-dense Correspondences for Visual Localization
Understanding the Limitations of CNN-based Absolute Camera Pose Regression
GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition
Towards a Deeper Understanding of Skeleton-based Gait Recognition
AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation
TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo
Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.