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/vita-epfl/unposed

공식 코드

Toward Reliable Human Pose Forecasting with Uncertainty

https://github.com/vitae-transformer/aptv2

공식 코드

APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond

https://github.com/vitae-transformer/qformer

공식 코드

Vision Transformer with Quadrangle Attention

https://github.com/vitae-transformer/vitpose

공식 코드

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

https://github.com/vitoralbiero/img2pose

공식 코드

img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation

https://github.com/vladpyatov/ihls

공식 코드

Robust Two-View Geometry Estimation with Implicit Differentiation

https://github.com/vpulab/spin

공식 코드

SPIN: Spacecraft Imagery for Navigation

https://github.com/vru2020/Pose_3D

공식 코드

Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry

https://github.com/vru2020/tm_hpe

공식 코드

Learning Temporal 3D Human Pose Estimation with Pseudo-Labels

https://github.com/w-shuoyan/evenhancer

공식 코드

EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events

https://github.com/wangjiongw/freeman_api

공식 코드

FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions

https://github.com/wangkua1/nemo-cvpr2023

공식 코드

NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action

https://github.com/warmspringwinds/tf-image-segmentation

공식 코드

Deep Residual Learning for Instrument Segmentation in Robotic Surgery

https://github.com/warmthless/split-deconvolution

공식 코드

Accelerating Generative Neural Networks on Unmodified Deep Learning Processors -- A Software Approach

https://github.com/wayne-mai/egoloc_v1

공식 코드

Hybrid Structure-from-Motion and Camera Relocalization for Enhanced Egocentric Localization

https://github.com/wei-mao-2019/LearnTrajDep

공식 코드

Learning Trajectory Dependencies for Human Motion Prediction

https://github.com/wei-mao-2019/contawaremotionpred

공식 코드

Contact-aware Human Motion Forecasting

https://github.com/wei-mao-2019/gsps

공식 코드

Generating Smooth Pose Sequences for Diverse Human Motion Prediction

https://github.com/weitong8591/vop

공식 코드

Breaking the Frame: Visual Place Recognition by Overlap Prediction

https://github.com/weizhenliubioinform/fish-phenotype-detect

공식 코드

Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture Breeding

https://github.com/wenbowen123/BundleTrack

공식 코드

BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models

https://github.com/wenbowen123/catgrasp

공식 코드

CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation

https://github.com/wenbowen123/icra20-hand-object-pose

공식 코드

Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands

https://github.com/wenbowen123/iros20-6d-pose-tracking

공식 코드

se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains

https://github.com/wenjiawang0312/zolly

공식 코드

Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction

https://github.com/wentaocheng-cv/cpf_localization

공식 코드

Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization

https://github.com/whisperyi/mmvr

공식 코드

EgoHand: Ego-centric Hand Pose Estimation and Gesture Recognition with Head-mounted Millimeter-wave Radar and IMUs

https://github.com/wholebody3d/wholebody3d

공식 코드

H3WB: Human3.6M 3D WholeBody Dataset and Benchmark

https://github.com/wielgosz-info/carla-pedestrians

공식 코드

CARLA-BSP: a simulated dataset with pedestrians

https://github.com/wiktormucha/SHARP

공식 코드

SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition

https://github.com/wiktormucha/effhandegonet

공식 코드

In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition

https://github.com/wimmerth/back-to-3d-few-shot-keypoints

공식 코드

Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features

https://github.com/wish44165/ReynoldsFlow

공식 코드

ReynoldsFlow: Exquisite Flow Estimation via Reynolds Transport Theorem

https://github.com/wkentaro/morefusion

공식 코드

MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion

https://github.com/wkentaro/reorientbot

공식 코드

ReorientBot: Learning Object Reorientation for Specific-Posed Placement

https://github.com/wkom/virtualpose

공식 코드

VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data

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