Skip to Main content Skip to Navigation
Poster communications

STADIE-Net: Stagewise Disparity Estimation from Stereo Event-based Cameras

Abhishek Tomy 1 Anshul Paigwar 1 Alessandro Renzaglia 1 Christian Laugier 1 
1 CHROMA - Robots coopératifs et adaptés à la présence humaine en environnements dynamiques
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
Abstract : Event-based cameras complement the frame based cameras in low-light conditions and high dynamic range scenarios that a robot can encounter for scene understanding and navigation. Apart from that, the comparatively cheaper cost in relation to a LiDAR sensor makes this a viable candidate when designing a sensor suite for a robot designed to operate in a dynamic environment. One of the challenges that the sensor suite needs to address is the ability to provide a 3D scene understanding of the environment that would enable the robot to localize obstacles in the environment. This work evaluates the accuracy with which an event-based camera can support this task by providing the disparity estimate between left and right camera frame which can be utilized to calculate the depth of surrounding. A new deep network architecture, named STADIE-Net is proposed that takes advantage of stagewise refinement and prediction of disparity using events from 2 neuromorphic cameras in a stereo setup. The method utilizes voxel grid representation for events as input and proposes a 4 stage network going from coarse to finer disparity prediction. The model is trained and evaluated on the publicly released DSEC dataset that has data recorded from multiple cities using event-based and frame-based cameras mounted on a moving vehicle. Experimental results show comparable accuracy with baseline method provided for DSEC dataset.
Document type :
Poster communications
Complete list of metadata
Contributor : Abhishek Tomy Connect in order to contact the contributor
Submitted on : Wednesday, October 6, 2021 - 4:16:37 PM
Last modification on : Monday, May 16, 2022 - 4:46:03 PM
Long-term archiving on: : Friday, January 7, 2022 - 7:27:50 PM


Files produced by the author(s)


  • HAL Id : hal-03368215, version 1



Abhishek Tomy, Anshul Paigwar, Alessandro Renzaglia, Christian Laugier. STADIE-Net: Stagewise Disparity Estimation from Stereo Event-based Cameras. CVPR 2021 - Conference on Computer Vision and Pattern Recognition, Jun 2021, Nashville, United States. pp.1-4, 2021. ⟨hal-03368215⟩



Record views


Files downloads