Papers with Code 아카이브

Pose Estimation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 17
평가표: 31
보존된 평가 기록: 235

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>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/yegyu-han/senseshift6d

공식 코드

SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations

https://github.com/yewzijian/regtr

공식 코드

REGTR: End-to-end Point Cloud Correspondences with Transformers

https://github.com/yhdang/dhrnet-multi-pose-estimation

공식 코드

DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation

https://github.com/yhdang/pose-estimation

공식 코드

Relation-Based Associative Joint Location for Human Pose Estimation in Videos

https://github.com/yhw-yhw/talkshow

공식 코드

Generating Holistic 3D Human Motion from Speech

https://github.com/yifanlu0227/coalign

공식 코드

Robust Collaborative 3D Object Detection in Presence of Pose Errors

https://github.com/yihui-he/epipolar-transformers

공식 코드

Epipolar Transformers

https://github.com/yiranran/Audio-driven-TalkingFace-HeadPose

공식 코드

Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose

https://github.com/yisuanwang/idea23d

공식 코드

Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs

https://github.com/yitongx/sinerf

공식 코드

SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstruction

https://github.com/ylochman/babelcalib

공식 코드

BabelCalib: A Universal Approach to Calibrating Central Cameras

https://github.com/yoavarad/mfad

공식 코드

Beyond the Benchmark: Detecting Diverse Anomalies in Videos

https://github.com/yoqim/pose_vireid

공식 코드

On Exploring Pose Estimation as an Auxiliary Learning Task for Visible-Infrared Person Re-identification

https://github.com/youmi-zym/go-slam

공식 코드

GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction

https://github.com/youngminPIL/rollback

공식 코드

Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification

https://github.com/yshMars/DistilPose

공식 코드

DistilPose: Tokenized Pose Regression with Heatmap Distillation

https://github.com/yu-jingrui/NToP

공식 코드

NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images

https://github.com/yu4u/kaggle-czii-4th

공식 코드

2.5D U-Net with Depth Reduction for 3D CryoET Object Identification

https://github.com/yuehan717/realviformer

공식 코드

RealViformer: Investigating Attention for Real-World Video Super-Resolution

https://github.com/yuezijie/stinet-space-time-video-super-resolution

공식 코드

Enhancing Space-time Video Super-resolution via Spatial-temporal Feature Interaction

https://github.com/yufu-wang/tram

공식 코드

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

https://github.com/yuhed/maps

공식 코드

MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection

https://github.com/yukimasano/PASS

공식 코드

PASS: An ImageNet replacement for self-supervised pretraining without humans

https://github.com/yuliangxiu/icon

공식 코드

ICON: Implicit Clothed humans Obtained from Normals

https://github.com/yumingj/C2-Matching

공식 코드

Reference-based Image and Video Super-Resolution via C2-Matching

https://github.com/yunfanLu/INR-Event-VSR

공식 코드

Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution

https://github.com/yunfanlu/hr-inr

공식 코드

HR-INR: Continuous Space-Time Video Super-Resolution via Event Camera

https://github.com/yunongLiu1/IKEA-Manuals-at-Work

공식 코드

IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos

https://github.com/yuqiao0303/fancy123

공식 코드

Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation

https://github.com/yuxwind/bigraphbody

공식 코드

Joint 3D Human Shape Recovery and Pose Estimation from a Single Image with Bilayer Graph

https://github.com/yw0208/STAF

공식 코드

STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusion

https://github.com/yw0208/W-HMR

공식 코드

W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration

https://github.com/yxymessi/dtc123

공식 코드

Diffusion Time-step Curriculum for One Image to 3D Generation

https://github.com/yysijie/st-gcn

공식 코드

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

https://github.com/yzcjtr/GeoNet

공식 코드

GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose

https://github.com/zaedulislam/gs-net

공식 코드

Iterative Graph Filtering Network for 3D Human Pose Estimation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.