https://github.com/hsp-iit/roft
공식 코드ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
6D Pose Estimation using RGB refers to the task of determining the six degree-of-freedom (6D) pose of an object in 3D space based on RGB images. This involves estimating the position and orientation of an object in a scene, and is a fundamental problem in computer vision and robotics. In this task, the goal is to estimate the 6D pose of an object given an RGB image of the object and the scene, which can be used for tasks such as robotic manipulation, augmented reality, and scene reconstruction.
<span style="color:grey; opacity: 0.6">( Image credit: Segmentation-driven 6D Object Pose Estimation )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking
Sim2Real Bilevel Adaptation for Object Surface Classification using Vision-Based Tactile Sensors
Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation
Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators
Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation
SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation
CVAM-Pose: Conditional Variational Autoencoder for Multi-Object Monocular Pose Estimation
CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation
Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild
Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision
GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting
Real-time Holistic Robot Pose Estimation with Unknown States
CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformers
Coupled Iterative Refinement for 6D Multi-Object Pose Estimation
Modular Quantization-Aware Training for 6D Object Pose Estimation
RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering
SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation
GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator
Estimating 6D Pose From Localizing Designated Surface Keypoints
T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects
Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation
BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands
se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation
Shape-Constraint Recurrent Flow for 6D Object Pose Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.