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/zahrag/SLOPE-KP

공식 코드

Self-supervised learning of object pose estimation using keypoint prediction

https://github.com/zakharos/DPOD

공식 코드

DPOD: 6D Pose Object Detector and Refiner

https://github.com/zc-alexfan/digit-interacting

공식 코드

Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation

https://github.com/zczcwh/DL-HPE

공식 코드

Deep Learning-Based Human Pose Estimation: A Survey

https://github.com/zczcwh/PoseFormer

공식 코드

3D Human Pose Estimation with Spatial and Temporal Transformers

https://github.com/zczcwh/feater

공식 코드

FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER

https://github.com/zczcwh/gtrs

공식 코드

A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose

https://github.com/zengbohan0217/ipdreamer

공식 코드

IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts

https://github.com/zengwang430521/DecoMR

공식 코드

3D Human Mesh Regression with Dense Correspondence

https://github.com/zengwang430521/tcformer

공식 코드

Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer

https://github.com/zerchen/AlignSDF

공식 코드

AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction

https://github.com/zerchen/gSDF

공식 코드

gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction

https://github.com/zetyquickly/DensePoseFnL

공식 코드

Making DensePose fast and light

https://github.com/zgspose/dsta

공식 코드

Video-Based Human Pose Regression via Decoupled Space-Time Aggregation

https://github.com/zh-mao/dsr

공식 코드

DSR: Direct Simultaneous Registration for Multiple 3D Images

https://github.com/zhang943/lpn-pytorch

공식 코드

Simple and Lightweight Human Pose Estimation

https://github.com/zhangboshen/A2J

공식 코드

A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image

https://github.com/zhangchenxu528/FACIAL

공식 코드

FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning

https://github.com/zhanghao5201/kdsm

공식 코드

Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching

https://github.com/zhangyuhong01/HumanMM-code

공식 코드

HumanMM: Global Human Motion Recovery from Multi-shot Videos

https://github.com/zhangyux15/4d_association

공식 코드

4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras

https://github.com/zhanhz/krf

공식 코드

PCKRF: Point Cloud Completion and Keypoint Refinement With Fusion Data for 6D Pose Estimation

https://github.com/zhaorw02/FlexiDreamer

공식 코드

FlexiDreamer: Single Image-to-3D Generation with FlexiCubes

https://github.com/zhaoxingZ/STVO

공식 코드

Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry

https://github.com/zhehengjianglancaster/amvur

공식 코드

A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image

https://github.com/zhengchen1999/dove

공식 코드

DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution

https://github.com/zhengli427/OKDHP

공식 코드

Online Knowledge Distillation for Efficient Pose Estimation

https://github.com/zhengxi-git/phase-slam

공식 코드

Phase-SLAM: Phase Based Simultaneous Localization and Mapping for Mobile Structured Light Illumination Systems

https://github.com/zhenpeiyang/RelativePose

공식 코드

Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion

https://github.com/zhenpeiyang/fvor

공식 코드

FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction

https://github.com/zhenpeiyang/hm3d-abo

공식 코드

HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction

https://github.com/zhezh/adafuse-3d-human-pose

공식 코드

AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild

https://github.com/zhiqiangdon/CU-Net

공식 코드

Quantized Densely Connected U-Nets for Efficient Landmark Localization

https://github.com/zhitengli/bidrn

공식 코드

BinaryHPE: 3D Human Pose and Shape Estimation via Binarization

https://github.com/zhongcl-thu/snake

공식 코드

SNAKE: Shape-aware Neural 3D Keypoint Field

https://github.com/zhonghuayi/ei-nexus_official

공식 코드

EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data

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