Papers with Code 아카이브
3D Human Shape Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 12
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Controlling Human Shape and Pose in Text-to-Image Diffusion Models via Domain Adaptation
AnthroNet: Conditional Generation of Humans via Anthropometrics
Shape of You: Precise 3D shape estimations for diverse body types
Super-resolution 3D Human Shape from a Single Low-Resolution Image
Accurate 3D Body Shape Regression using Metric and Semantic Attributes
ICON: Implicit Clothed humans Obtained from Normals
Human Performance Capture from Monocular Video in the Wild
A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose
Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images
Leveraging MoCap Data for Human Mesh Recovery
Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild
DC-GNet: Deep Mesh Relation Capturing Graph Convolution Network for 3D Human Shape Reconstruction
LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering
Learning Local Recurrent Models for Human Mesh Recovery
Everybody Is Unique: Towards Unbiased Human Mesh Recovery
Body Meshes as Points
AGORA: Avatars in Geography Optimized for Regression Analysis
KAMA: 3D Keypoint Aware Body Mesh Articulation
Temporal Consistency Loss for High Resolution Textured and Clothed 3DHuman Reconstruction from Monocular Video
Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild
Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People
Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild
Monocular Real-Time Volumetric Performance Capture
Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Data
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization
Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop
Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images
3DPeople: Modeling the Geometry of Dressed Humans
End-to-end Recovery of Human Shape and Pose
Model-based anthropometry: Predicting measurements from 3D human scans in multiple poses
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.