← Monocular 3D Human Pose Estimation
Papers with Code · CC BY-SA 4.0

Human3.6M

아카이브 평가 52건 · 마지막 적재/변경

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델원본 지표·값논문구현
SIM (SH detections FT) (MA)
Average MPJPE (mm)
62.9
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
A simple yet effective baseline for 3d human pose estimation
2017-05-08
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14
Bundle Adjustment (GTi)
Average MPJPE (mm)
63.3
Exploiting temporal context for 3D human pose estimation in the wild
2019-05-10
코드 1
SelecSLS
Average MPJPE (mm)
63.6
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera
2019-07-01
코드 1 · 코드 2 · 코드 3 · 코드 4
Weakly Supervised Transfer Learning
Average MPJPE (mm)
64.9
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
2017-04-08
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
VIBE
Average MPJPE (mm)
65.6
Use Video Sequence
Yes
Frames Needed
16
Need Ground Truth 2D Pose
No
VIBE: Video Inference for Human Body Pose and Shape Estimation
2019-12-11
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
GraphCMR
Average MPJPE (mm)
74.7
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
Convolutional Mesh Regression for Single-Image Human Shape Reconstruction
2019-05-08
코드 1 · 코드 2
Projected-pose belief maps + 2D fusion layers
Average MPJPE (mm)
88.39
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
2017-01-01
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11
RepNet
Average MPJPE (mm)
89.9
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation
2019-02-26
코드 1
Dual-source approach
Average MPJPE (mm)
97.39
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
A Dual-Source Approach for 3D Human Pose Estimation from a Single Image
2017-05-08
연결 없음
Sparseness Meets Deepness
Average MPJPE (mm)
113.01
Use Video Sequence
Yes
Frames Needed
300
Need Ground Truth 2D Pose
No
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
2015-11-30
코드 1
HMR
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
End-to-end Recovery of Human Shape and Pose
2017-12-18
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10
Neural Body Fitting (NBF)
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation
2018-08-17
코드 1 · 코드 2
SMPLify (dense)
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
Unite the People: Closing the Loop Between 3D and 2D Human Representations
2017-01-10
코드 1 · 코드 2
Ordinal Depth Supervision
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
Ordinal Depth Supervision for 3D Human Pose Estimation
2018-05-10
코드 1
Adversarial Learning
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
3D Human Pose Estimation in the Wild by Adversarial Learning
2018-03-26
연결 없음
Moon et. al.
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image
2019-07-26
코드 1 · 코드 2 · 코드 3 · 코드 4
PoseAug
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation
2021-05-06
코드 1
HEMlets Pose
Use Video Sequence
No
Frames Needed
1
Need Ground Truth 2D Pose
No
HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation
2019-10-26
연결 없음
Ray3D
Use Video Sequence
Yes
Frames Needed
9
Need Ground Truth 2D Pose
No
Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization
2022-03-22
코드 1
Bundle Adjustment
Use Video Sequence
Yes
Frames Needed
190
Need Ground Truth 2D Pose
No
Exploiting temporal context for 3D human pose estimation in the wild
2019-05-10
코드 1
Neural Body Fitting (NBF)
PA-MPJPE
59.9
Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation
2018-08-17
코드 1 · 코드 2
SMPLify (dense)
PA-MPJPE
80.7
Unite the People: Closing the Loop Between 3D and 2D Human Representations
2017-01-10
코드 1 · 코드 2