https://bitbucket.org/fafz/bayesian-icp
공식 코드Speeding Up Iterative Closest Point Using Stochastic Gradient Descent
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.
A common benchmark for this task is MPII Human Pose
<span style="color:grey; opacity: 0.6">( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Speeding Up Iterative Closest Point Using Stochastic Gradient Descent
Stein ICP for Uncertainty Estimation in Point Cloud Matching
Human pose estimation via Convolutional Part Heatmap Regression
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
Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation
Occlusion-Invariant Rotation-Equivariant Semi-Supervised Depth Based Cross-View Gait Pose Estimation
AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
Real-time Pose Estimation from Images for Multiple Humanoid Robots
Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensors
Stillleben: Realistic Scene Synthesis for Deep Learning in Robotics
SynPick: A Dataset for Dynamic Bin Picking Scene Understanding
When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks
3D human pose estimation from depth maps using a deep combination of poses
LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments
Neural Refinement for Absolute Pose Regression with Feature Synthesis
NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior
PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction
AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild
Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
Two-Stream Action Recognition-Oriented Video Super-Resolution
Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection
NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation
Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation
WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.