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/franknb/Self-attention-DCGAN

Non-local Neural Networks

https://github.com/freedombenLiu/DensePose

DensePose: Dense Human Pose Estimation In The Wild

https://github.com/frgfm/Holocron

Rotate to Attend: Convolutional Triplet Attention Module

https://github.com/fsafe/Capstone

https://github.com/fuenwang/3D-BoundingBox

3D Bounding Box Estimation Using Deep Learning and Geometry

https://github.com/fzi-forschungszentrum-informatik/mrf

SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth

https://github.com/gabrevaya/LatentDiffEq

Neural Ordinary Differential Equations

https://github.com/gabrevaya/LatentDiffEq.jl

Neural Ordinary Differential Equations

https://github.com/garrickbrazil/kinematic3d

Kinematic 3D Object Detection in Monocular Video

https://github.com/garroud/human-motion-prediction-pytorch

On human motion prediction using recurrent neural networks

https://github.com/garyzhao/FRGAN

Learning to Forecast and Refine Residual Motion for Image-to-Video Generation

https://github.com/gasteigerjo/ocp

The Open Catalyst 2020 (OC20) Dataset and Community Challenges

https://github.com/gauraviiita/Visualization-of-Human3.6M-Dataset

On human motion prediction using recurrent neural networks

https://github.com/gchb2012/VQA

Let's Transfer Transformations of Shared Semantic Representations

https://github.com/geaxgx/depthai_blazepose

BlazePose: On-device Real-time Body Pose tracking

https://github.com/geoffsmith/gan-ode

Neural Ordinary Differential Equations

https://github.com/geopavlakos/TexturePose

TexturePose: Supervising Human Mesh Estimation with Texture Consistency

https://github.com/geopavlakos/c2f-vol-demo

Stacked Hourglass Networks for Human Pose Estimation

https://github.com/geopavlakos/c2f-vol-train

Stacked Hourglass Networks for Human Pose Estimation

https://github.com/geopavlakos/hamer

Reconstructing Hands in 3D with Transformers

https://github.com/geopavlakos/object3d

Stacked Hourglass Networks for Human Pose Estimation

https://github.com/geopavlakos/ordinal-pose3d

Stacked Hourglass Networks for Human Pose Estimation

https://github.com/george-gca/sr-pytorch-lightning

Image Super-Resolution Using Deep Convolutional Networks

https://github.com/germain-hug/NRE

Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation

https://github.com/gfjiangly/CenterNet

Objects as Points

https://github.com/gidobot/SilhoNet

SilhoNet: An RGB Method for 6D Object Pose Estimation

https://github.com/github-zbx/ST-GCN

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

https://github.com/gitting-it-right/gaussian_centernet

Objects as Points

https://github.com/godspeedcurry/lung-nodule-detection

https://github.com/gogojjh/ESVO_extension

Event-based Stereo Visual Odometry

https://github.com/gongzix/neuroclips

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models

https://github.com/goodxue/CenterNet

Objects as Points

https://github.com/google-coral/project-posenet

PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model

https://github.com/google-research/google-research/tree/master/poem

View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose

https://github.com/google-research/sparf

Learning Accurate Dense Correspondences and When to Trust Them

https://github.com/google/samurai

SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections

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