1. [Publications](/index.php/publications)
2. Multi-View Fusion for Multi-Level Robotic Scene Understanding
 
 # Multi-View Fusion for Multi-Level Robotic Scene Understanding

  ![](/sites/default/files/styles/wide/public/publications/mvml.jpg?itok=cnXwr0OP)

 We present a system for multi-level scene awareness for robotic manipulation. Given a sequence of camera-in-hand RGB images, the system calculates three types of information: 1) a point cloud representation of all the surfaces in the scene, for the purpose of obstacle avoidance. 2) the rough pose of unknown objects from categories corresponding to primitive shapes (e.g., cuboids and cylinders), and 3) full 6-DoF pose of known objects. By developing and fusing recent techniques in these domains, we provide a rich scene representation for robot awareness. We demonstrate the importance of each of these modules, their complementary nature, and the potential benefits of the system in the context of robotic manipulation.



 ## Authors



Yunzhi Lin (NVIDIA, Georgia Institute of Technology)

[Jonathan Tremblay](/index.php/person/jonathan-tremblay)

[Stephen Tyree](/index.php/person/stephen-tyree)

Patricio A. Vela (Georgia Institute of Technology)

[Stan Birchfield](/index.php/person/stan-birchfield)

 

 

 ## Publication Date



Wednesday, September 15, 2021

 

 ## Published in



[IROS 2021](https://www.iros2021.org/)

 

 ## Research Area



[Computer Vision](/index.php/research-area/computer-vision)

[Robotics](/index.php/research-area/robotics)

 

 

 ## External Links



[arXiv](https://arxiv.org/abs/2103.13539)