Papers with Code 아카이브
Pose Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
복합 과운동 장애의 다중 레이블 인식을 위한 심층 학습 기반 포즈 추정
등대 유도 구조적 추론을 통한 위상 인식 스켈레톤 검출
Sketch2Arti: CAD 객체의 스케치 기반 관절 모델링
픽셀에서 뉴턴까지: 단안 영상으로부터 생체 관절 접촉력 예측
RigPAPR: 고정 시점 비디오로부터 정적 신경망 포인트 클라우드의 리그 기반 애니메이션
SAR 영상에서 항공기 표적의 물리 기반 의미적 산란 구조 이해
강인한 6자유도 파지 자세 추정을 위한 교차 시점 융합 프레임워크
EgoPressDiff: 자기중심 시점 UV 도메인 손 압력 추정을 위한 멀티모달 비디오 디퓨전
스켈레톤을 넘어서: Same2X 학습 전략으로 드라이빙 비디오에서 애니메이션을 직접 학습
From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation
AthleticsPose: Authentic Sports Motion Dataset on Athletic Field and Evaluation of Monocular 3D Pose Estimation Ability
GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training
DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model
Revisiting Reliability in the Reasoning-based Pose Estimation Benchmark
$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning
SEPose: A Synthetic Event-based Human Pose Estimation Dataset for Pedestrian Monitoring
SGLoc: Semantic Localization System for Camera Pose Estimation from 3D Gaussian Splatting Representation
BRUM: Robust 3D Vehicle Reconstruction from 360 Sparse Images
Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation
SpatialTrackerV2: 3D Point Tracking Made Easy
PhysX: Physical-Grounded 3D Asset Generation
Joint angle model based learning to refine kinematic human pose estimation
GKNet: Graph-based Keypoints Network for Monocular Pose Estimation of Non-cooperative Spacecraft
KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model
Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Textures
FPC-Net: Revisiting SuperPoint with Descriptor-Free Keypoint Detection via Feature Pyramids and Consistency-Based Implicit Matching
Self-supervised pretraining of vision transformers for animal behavioral analysis and neural encoding
VST-Pose: A Velocity-Integrated Spatiotem-poral Attention Network for Human WiFi Pose Estimation
PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment
Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection
MK-Pose: Category-Level Object Pose Estimation via Multimodal-Based Keypoint Learning
Event-RGB Fusion for Spacecraft Pose Estimation Under Harsh Lighting
DreamArt: Generating Interactable Articulated Objects from a Single Image
LMPNet for Weakly-supervised Keypoint Discovery
Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.