Corpus ID: 198179952

Not Only Look But Observe: Variational Observation Model of Scene-Level 3D Multi-Object Understanding for Probabilistic SLAM

  title={Not Only Look But Observe: Variational Observation Model of Scene-Level 3D Multi-Object Understanding for Probabilistic SLAM},
  author={Hyeonwoo Yu and Beomhee Lee},
We present NOLBO, a variational observation model estimation for 3D multi-object from 2D single shot. Previous probabilistic instance-level understandings mainly consider the single-object image, not single shot with multi-object; relations between objects and the entire scene are out of their focus. The objectness of each observation also hardly join their model. Therefore, we propose a method to approximate the Bayesian observation model of scene-level 3D multi-object understanding. By… Expand


A Variational Observation Model of 3D Object for Probabilistic Semantic SLAM
  • H. W. Yu, B. H. Lee
  • Computer Science, Engineering
  • 2019 International Conference on Robotics and Automation (ICRA)
  • 2019
This work approximate the observation model of a 3D object with a tractable distribution to enable the complete formulation of probabilistic semantic SLAM and estimates the variational likelihood from the 2D image of the object to exploit its observed single view. Expand
A Variational Feature Encoding Method of 3D Object for Probabilistic Semantic SLAM
  • H. W. Yu, Beom-Hee Lee
  • Computer Science
  • 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2018
A feature encoding method of complex 3D objects for high-level semantic features to enable the numerical analysis for the Bayesian inference and to analyze the approximated distributions and encoded features, which perform classification with maximum likelihood estimation and shape retrieval. Expand
Constructing Category-Specific Models for Monocular Object-SLAM
A new paradigm for real-time object-oriented SLAM with a monocular camera is presented and the first results of an instance-independent monocular object-SLAM system are shown and the benefits it enjoys over feature-based SLAM methods are shown. Expand
3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare
A differentiable Render-and-Compare loss is proposed that allows 3D shape and pose to be learned with 2D supervision and produces a compact 3D representation of the scene, which can be readily used for applications like autonomous driving. Expand
SLAM++: Simultaneous Localisation and Mapping at the Level of Objects
The object graph enables predictions for accurate ICP-based camera to model tracking at each live frame, and efficient active search for new objects in currently undescribed image regions, as well as the generation of an object level scene description with the potential to enable interaction. Expand
Data-driven 3D Voxel Patterns for object category recognition
A novel object representation is proposed, 3D Voxel Pattern (3DVP), that jointly encodes the key properties of objects including appearance,3D shape, viewpoint, occlusion and truncation. Expand
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. Expand
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. Expand
Multimodal Semantic SLAM with Probabilistic Data Association
This work proposes a solution that represents hypotheses as multiple modes of an equivalent non-Gaussian sensor model that solves the resulting non- Gaussian inference problem under ambiguous data associations using nonparametric belief propagation. Expand
3D Bounding Box Estimation Using Deep Learning and Geometry
Although conceptually simple, this method outperforms more complex and computationally expensive approaches that leverage semantic segmentation, instance level segmentation and flat ground priors and produces state of the art results for 3D viewpoint estimation on the Pascal 3D+ dataset. Expand