https://github.com/val-iisc/ssl_3d_recon
공식 코드From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks
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.
From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks
OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving
PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation
Multi-camera Torso Pose Estimation using Graph Neural Networks
Comparative Evaluation of 3D Reconstruction Methods for Object Pose Estimation
SymFormer: End-to-end symbolic regression using transformer-based architecture
NeuriCam: Key-Frame Video Super-Resolution and Colorization for IoT Cameras
ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning
Monocular Expressive Body Regression through Body-Driven Attention
Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
HTNet: Human Topology Aware Network for 3D Human Pose Estimation
Absolute Human Pose Estimation with Depth Prediction Network
Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People
Multi-Person Absolute 3D Human Pose Estimation with Weak Depth Supervision
GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation
Improving the matching of deformable objects by learning to detect keypoints
Learning to Detect Good Keypoints to Match Non-Rigid Objects in RGB Images
Pola4All: survey of polarimetric applications and an open-source toolkit to analyze polarization
Center Direction Network for Grasping Point Localization on Cloths
Beyond Audio and Pose: A General-Purpose Framework for Video Synchronization
HiFi-CS: Towards Open Vocabulary Visual Grounding For Robotic Grasping Using Vision-Language Models
PCRNet: Point Cloud Registration Network using PointNet Encoding
PCRNet: Point Cloud Registration Network using PointNet Encoding
PCRNet: Point Cloud Registration Network using PointNet Encoding
One Framework to Register Them All: PointNet Encoding for Point Cloud Alignment
Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning
MotionMap: Representing Multimodality in Human Pose Forecasting
TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression
A generic diffusion-based approach for 3D human pose prediction in the wild
Multi-Transmotion: Pre-trained Model for Human Motion Prediction
OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association
OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.