• Corpus ID: 208138925

Fast 3D Pose Refinement with RGB Images

  title={Fast 3D Pose Refinement with RGB Images},
  author={Abhinav Jain and Frank Dellaert},
Pose estimation is a vital step in many robotics and perception tasks such as robotic manipulation, autonomous vehicle navigation, etc. Current state-of-the-art pose estimation methods rely on deep neural networks with complicated structures and long inference times. While highly robust, they require computing power often unavailable on mobile robots. We propose a CNN-based pose refinement system which takes a coarsely estimated 3D pose from a computationally cheaper algorithm along with a… 
1 Citations
Calibration of Diverse Tracking Systems to Enable Local Collaborative Mixed Reality Applications
The proposed trajectory-based algorithm provides reliable and precise results when compared to SfM or marker based algorithms, and enables local multi user collaboration for all six degrees of freedom (DOF) MR devices.


3D Pose Regression Using Convolutional Neural Networks
It is argued that 3D pose is continuous and can be solved in a regression framework if done with the right representation, data augmentation and loss function.
Deep Model-Based 6D Pose Refinement in RGB
A new visual loss is proposed that drives the pose update by aligning object contours, thus avoiding the definition of any explicit appearance model and producing pose accuracies that come close to 3D ICP without the need for depth data.
6-DoF object pose from semantic keypoints
A novel approach to estimating the continuous six degree of freedom (6-DoF) pose (3D translation and rotation) of an object from a single RGB image by combining semantic keypoints predicted by a convolutional network with a deformable shape model.
Real-Time Seamless Single Shot 6D Object Pose Prediction
A single-shot approach for simultaneously detecting an object in an RGB image and predicting its 6D pose without requiring multiple stages or having to examine multiple hypotheses is proposed, which substantially outperforms other recent CNN-based approaches when they are all used without postprocessing.
Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes
A framework for automatic modeling, detection, and tracking of 3D objects with a Kinect and shows how to build the templates automatically from 3D models, and how to estimate the 6 degrees-of-freedom pose accurately and in real-time.
Training a Feedback Loop for Hand Pose Estimation
An entirely data-driven approach to estimating the 3D pose of a hand given a depth image is proposed, which outperforms state-of-the-art methods, and is efficient as the implementation runs at over 400 fps on a single GPU.
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
This work introduces PoseCNN, a new Convolutional Neural Network for 6D object pose estimation, which is highly robust to occlusions, can handle symmetric objects, and provide accurate pose estimation using only color images as input.
BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth
  • Mahdi Rad, V. Lepetit
  • Computer Science
    2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
A novel method for 3D object detection and pose estimation from color images only that uses segmentation to detect the objects of interest in 2D even in presence of partial occlusions and cluttered background and is the first to report results on the Occlusion dataset using color imagesonly.
Viewpoints and keypoints
The problem of pose estimation for rigid objects in terms of determining viewpoint to explain coarse pose and keypoint prediction to capture the finer details is characterized and it is demonstrated that leveraging viewpoint estimates can substantially improve local appearance based keypoint predictions.
Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image
A regularized, auto-context regression framework is developed which iteratively reduces uncertainty in object coordinate and object label predictions and an efficient way to marginalize object coordinate distributions over depth is introduced to deal with missing depth information.