https://github.com/lkeab/gsnet
공식 코드GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Image credit: GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision , ECCV'20
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision
3D Human Pose Estimation in RGBD Images for Robotic Task Learning
Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
Visual Pursuit Control based on Gaussian Processes with Switched Motion Trajectories
Real-time marker-less multi-person 3D pose estimation in RGB-Depth camera networks
Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion
VIBE: Video Inference for Human Body Pose and Shape Estimation
Enhancing Egocentric 3D Pose Estimation with Third Person Views
RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation
PoP-Net: Pose over Parts Network for Multi-Person 3D Pose Estimation from a Depth Image
Adapted Human Pose: Monocular 3D Human Pose Estimation with Zero Real 3D Pose Data
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
GST: Precise 3D Human Body from a Single Image with Gaussian Splatting Transformers
Domain Randomization for Scene-Specific Car Detection and Pose Estimation
DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation
Local and Global Point Cloud Reconstruction for 3D Hand Pose Estimation
Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation
Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objects
STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose Estimation
Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting
Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration
HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media
A simple yet effective baseline for 3d human pose estimation
Multi-Person Absolute 3D Human Pose Estimation with Weak Depth Supervision
FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions
VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data
DeProPose: Deficiency-Proof 3D Human Pose Estimation via Adaptive Multi-View Fusion
Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images
Quater-GCN: Enhancing 3D Human Pose Estimation with Orientation and Semi-supervised Training
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.