SOTAVerified

6D Pose Estimation using RGB

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.

( Image credit: Segmentation-driven 6D Object Pose Estimation )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 233 papers

TitleStatusHype
Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)Code1
CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement TransformersCode1
Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose EstimationCode1
DCL-Net: Deep Correspondence Learning Network for 6D Pose EstimationCode1
CASAPose: Class-Adaptive and Semantic-Aware Multi-Object Pose EstimationCode1
EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approachCode1
BOP: Benchmark for 6D Object Pose EstimationCode1
DexYCB: A Benchmark for Capturing Hand Grasping of ObjectsCode1
BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D ModelsCode1
CosyPose: Consistent multi-view multi-object 6D pose estimationCode1
Show:102550
← PrevPage 2 of 24Next →

No leaderboard results yet.