TriStereoNet: A Trinocular Framework for Multi-baseline Disparity Estimation

24 Nov 2021  ยท  Faranak Shamsafar, Andreas Zell ยท

Stereo vision is an effective technique for depth estimation with broad applicability in autonomous urban and highway driving. While various deep learning-based approaches have been developed for stereo, the input data from a binocular setup with a fixed baseline are limited. Addressing such a problem, we present an end-to-end network for processing the data from a trinocular setup, which is a combination of a narrow and a wide stereo pair. In this design, two pairs of binocular data with a common reference image are treated with shared weights of the network and a mid-level fusion. We also propose a Guided Addition method for merging the 4D data of the two baselines. Additionally, an iterative sequential self-supervised and supervised learning on real and synthetic datasets is presented, making the training of the trinocular system practical with no need to ground-truth data of the real dataset. Experimental results demonstrate that the trinocular disparity network surpasses the scenario where individual pairs are fed into a similar architecture. Code and dataset: https://github.com/cogsys-tuebingen/tristereonet.

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on Stereo Depth Estimation on KITTI2015 (D1-all All metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Stereo Depth Estimation KITTI2015 TriStereoNet D1-all All 2.35 # 1
D1-all Noc 2.09 # 1
Stereo Depth Estimation KITTI 2015 TriStereoNet D1-all All 2.35 # 2
D1-all Noc 2.09 # 2

Methods


No methods listed for this paper. Add relevant methods here