https://github.com/microsoft/MeshTransformer
공식 코드End-to-End Human Pose and Mesh Reconstruction with Transformers
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Hand pose estimation is the task of finding the joints of the hand from an image or set of video frames.
<span style="color:grey; opacity: 0.6">( Image credit: Pose-REN )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
End-to-End Human Pose and Mesh Reconstruction with Transformers
Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation
DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation
Efficiently Creating 3D Training Data for Fine Hand Pose Estimation
Robustness Evaluation in Hand Pose Estimation Models using Metamorphic Testing
TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation
ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation
Orientation Attentive Robotic Grasp Synthesis with Augmented Grasp Map Representation
Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Models
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers
EventHands: Real-Time Neural 3D Hand Pose Estimation from an Event Stream
FINNger -- Applying artificial intelligence to ease math learning for children
AttentionHand: Text-driven Controllable Hand Image Generation for 3D Hand Reconstruction in the Wild
WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild
DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation
Interacting Hand-Object Pose Estimation via Dense Mutual Attention
FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
Diffusion-based Generation, Optimization, and Planning in 3D Scenes
Local and Global Point Cloud Reconstruction for 3D Hand Pose Estimation
Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time
ContactGen: Generative Contact Modeling for Grasp Generation
Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.