Papers with Code 아카이브
3D Multi-Person Pose Estimation (root-relative)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 20
This task aims to solve root-relative 3D multi-person pose estimation (person-centric coordinate system). No ground truth human bounding box and human root joint coordinates are used during testing stage.
<span style="color:grey; opacity: 0.6">( Image credit: RootNet )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation
Dynamic Graph Reasoning for Multi-person 3D Pose Estimation
Dual networks based 3D Multi-Person Pose Estimation from Monocular Video
Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
Deep Monocular 3D Human Pose Estimation via Cascaded Dimension-Lifting
Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks
Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos
Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People
PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation
SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation
HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation
HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization
Multi-Person Absolute 3D Human Pose Estimation with Weak Depth Supervision
Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image
Absolute Human Pose Estimation with Depth Prediction Network
Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB
Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.