https://github.com/Arthur151/DSD-SATN
공식 코드Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Estimate 3D body mesh from images
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation
PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop
Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Losses
DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery
Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery
Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models
CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation
Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video
Deep learning for 3D human pose estimation and mesh recovery: A survey
Multimodal Active Measurement for Human Mesh Recovery in Close Proximity
Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot
GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling
Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation
TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation
Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views
ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization
Humans in 4D: Reconstructing and Tracking Humans with Transformers
Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms
Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery
NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action
Self-supervised 3D Human Mesh Recovery from Noisy Point Clouds
JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.