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/aimi-lab/robust-pose-estimator

공식 코드

Learning How To Robustly Estimate Camera Pose in Endoscopic Videos

https://github.com/aiotgroup/xrfv2

공식 코드

XRF V2: A Dataset for Action Summarization with Wi-Fi Signals, and IMUs in Phones, Watches, Earbuds, and Glasses

https://github.com/ais-bonn/jetsontrtperception

공식 코드

3D Semantic Scene Perception using Distributed Smart Edge Sensors

https://github.com/ais-bonn/smartedgesensor3dsceneperception

공식 코드

3D Semantic Scene Perception using Distributed Smart Edge Sensors

https://github.com/akanazawa/human_dynamics

공식 코드

Learning 3D Human Dynamics from Video

https://github.com/akashsengupta1997/STRAPS-3DHumanShapePose

공식 코드

Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild

https://github.com/akashsengupta1997/hierarchicalprobabilistic3dhuman

공식 코드

Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild

https://github.com/akashsengupta1997/humaniflow

공식 코드

HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation

https://github.com/akschion/PoseGravity

공식 코드

PoseGravity: Pose Estimation from Points and Lines with Axis Prior

https://github.com/alanlusun/few-shot-keypoint-detection

공식 코드

Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species

https://github.com/alanlusun/openkd

공식 코드

OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection

https://github.com/aleflabo/MoCoDAD

공식 코드

Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection

https://github.com/aleksispi/pose-drl

공식 코드

Deep Reinforcement Learning for Active Human Pose Estimation

https://github.com/alessiosam/chico-poseforecasting

공식 코드

Pose Forecasting in Industrial Human-Robot Collaboration

https://github.com/alexandrebanks6/dv-stear_public

공식 코드

Setup-Invariant Augmented Reality for Teaching by Demonstration with Surgical Robots

https://github.com/alexandrosstergiou/adaPool

공식 코드

AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling

https://github.com/alexhang212/3d-muppet

공식 코드

3D-MuPPET: 3D Multi-Pigeon Pose Estimation and Tracking

https://github.com/alexhang212/dataset-3dpop

공식 코드

3D-POP - An automated annotation approach to facilitate markerless 2D-3D tracking of freely moving birds with marker-based motion capture

https://github.com/alexthebad/ap10k

공식 코드

AP-10K: A Benchmark for Animal Pose Estimation in the Wild

https://github.com/alexzzhu/EventGAN

공식 코드

EventGAN: Leveraging Large Scale Image Datasets for Event Cameras

https://github.com/alibaba-damo-academy/med_query

공식 코드

Med-Query: Steerable Parsing of 9-DoF Medical Anatomies with Query Embedding

https://github.com/alimd94/fedvsr

공식 코드

FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolution

https://github.com/aliprf/ASMNet

공식 코드

ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation

https://github.com/alivaramesh/MixtureDenseRegression

공식 코드

Mixture Dense Regression for Object Detection and Human Pose Estimation

https://github.com/aliyoussef97/silk-prp

공식 코드

NeRF-Supervised Feature Point Detection and Description

https://github.com/allenai/grit_official

공식 코드

GRIT: General Robust Image Task Benchmark

https://github.com/alpha-vllm/llama2-accessory

공식 코드

SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models

https://github.com/alterpang/multi_orb_slam

공식 코드

Multicam-SLAM: Non-overlapping Multi-camera SLAM for Indirect Visual Localization and Navigation

https://github.com/amanchadha/iSeeBetter

공식 코드

iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks

https://github.com/amathislab/BUCTD

공식 코드

Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity

https://github.com/amathislab/hoisdf

공식 코드

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

https://github.com/amathislab/poet

공식 코드

End-to-End Trainable Multi-Instance Pose Estimation with Transformers

https://github.com/amir32002/3D_Street_View

공식 코드

Generic 3D Representation via Pose Estimation and Matching

https://github.com/amyxlase/relpose-plus-plus

공식 코드

RelPose++: Recovering 6D Poses from Sparse-view Observations

https://github.com/amzn/mrc-net-6d-pose

공식 코드

MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation

https://github.com/andresprados/spiga

공식 코드

Shape Preserving Facial Landmarks with Graph Attention Networks

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