6D Pose Estimation using RGB
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 6
- 보존된 평가 기록
- 45
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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions
MatchNorm: Learning-based Point Cloud Registration for 6D Object Pose Estimation in the Real World
FS6D: Few-Shot 6D Pose Estimation of Novel Objects
RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization
EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation
Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation
GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting
NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation
Weakly Supervised Learning of Keypoints for 6D Object Pose Estimation
OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimation
Adversarial samples for deep monocular 6D object pose estimation
Rigidity Preserving Image Transformations and Equivariance in Perspective
Pose Estimation of Specific Rigid Objects
Polarimetric Pose Prediction
ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimation
ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking
Occlusion-Robust Object Pose Estimation with Holistic Representation
6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learning
Learning Stereopsis from Geometric Synthesis for 6D Object Pose Estimation
StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimation
KDFNet: Learning Keypoint Distance Field for 6D Object Pose Estimation
Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networks
SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation
BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
6D Object Pose Estimation using Keypoints and Part Affinity Fields
Multistream ValidNet: Improving 6D Object Pose Estimation by Automatic Multistream Validation
Investigations on Output Parameterizations of Neural Networks for Single Shot 6D Object Pose Estimation
DexYCB: A Benchmark for Capturing Hand Grasping of Objects
Wide-Depth-Range 6D Object Pose Estimation in Space
RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering
Generating Annotated Training Data for 6D Object Pose Estimation in Operational Environments with Minimal User Interaction
MBAPose: Mask and Bounding-Box Aware Pose Estimation of Surgical Instruments with Photorealistic Domain Randomization
FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism
GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.