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/ethnhe/FS6D-PyTorch

공식 코드

FS6D: Few-Shot 6D Pose Estimation of Novel Objects

https://github.com/ethnhe/PVN3D

공식 코드

PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation

https://github.com/ethz-asl/3d3l

공식 코드

3D3L: Deep Learned 3D Keypoint Detection and Description for LiDARs

https://github.com/ethz-asl/hierarchical_loc

공식 코드

Leveraging Deep Visual Descriptors for Hierarchical Efficient Localization

https://github.com/ethz-asl/neusurfemb

공식 코드

NeuSurfEmb: A Complete Pipeline for Dense Correspondence-based 6D Object Pose Estimation without CAD Models

https://github.com/ethz-asl/object_keypoints

공식 코드

Semi-automatic 3D Object Keypoint Annotation and Detection for the Masses

https://github.com/eugenelet/crfp

공식 코드

Cross-Resolution Flow Propagation for Foveated Video Super-Resolution

https://github.com/eunjnnn/bfstvsr

공식 코드

BF-STVSR: B-Splines and Fourier-Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution

https://github.com/evendrow/somoformer

공식 코드

SoMoFormer: Multi-Person Pose Forecasting with Transformers

https://github.com/ewrfcas/casmtr

공식 코드

Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints

https://github.com/exscientia/plif_validity

공식 코드

Assessing interaction recovery of predicted protein-ligand poses

https://github.com/eyalnaor/DeepTemporalSR

공식 코드

Across Scales & Across Dimensions: Temporal Super-Resolution using Deep Internal Learning

https://github.com/fabbrimatteo/LoCO

공식 코드

Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation

https://github.com/fabro66/GAST-Net-3DPoseEstimation

공식 코드

A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video

https://github.com/facebookresearch/AnimalAvatar

공식 코드

Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos

https://github.com/facebookresearch/PoseWarper

공식 코드

Learning Temporal Pose Estimation from Sparsely-Labeled Videos

https://github.com/facebookresearch/QuaterNet

공식 코드

QuaterNet: A Quaternion-based Recurrent Model for Human Motion

https://github.com/facebookresearch/VideoPose3D

공식 코드

3D human pose estimation in video with temporal convolutions and semi-supervised training

https://github.com/facebookresearch/assemblyhands-toolkit

공식 코드

Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects

https://github.com/facebookresearch/body2hands

공식 코드

Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics

https://github.com/facebookresearch/detectron2/tree/main/projects/DensePose

공식 코드

Continuous Surface Embeddings

https://github.com/facebookresearch/eft

공식 코드

Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation

https://github.com/facebookresearch/emg2pose

공식 코드

emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation

https://github.com/facebookresearch/fast3r

공식 코드

Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

https://github.com/facebookresearch/frankmocap

공식 코드

FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration

https://github.com/facebookresearch/meshtalk

공식 코드

MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement

https://github.com/facebookresearch/multi_view_active_learning

공식 코드

Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Training

https://github.com/facebookresearch/phosa

공식 코드

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

https://github.com/facebookresearch/pifuhd

공식 코드

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

https://github.com/facebookresearch/projectaria_tools

공식 코드

Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception

https://github.com/facebookresearch/relative_pose_dataset

공식 코드

Instant Visual Odometry Initialization for Mobile AR

https://github.com/facebookresearch/silk

공식 코드

SiLK -- Simple Learned Keypoints

https://github.com/facebookresearch/video-nonlocal-net

공식 코드

Non-local Neural Networks

https://github.com/facebookresearch/xR-EgoPose

공식 코드

A Survey on 3D Egocentric Human Pose Estimation

https://github.com/facebookresearch/you2me

공식 코드

You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions

https://github.com/fairydance/deeprli

공식 코드

DeepRLI: A Multi-objective Framework for Universal Protein--Ligand Interaction Prediction

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