Saved in:
Bibliographic Details
Main Authors: Jahedi, Azin, Mehl, Lukas, Rivinius, Marc, Bruhn, Andrés
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2207.12163
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908382126931968
author Jahedi, Azin
Mehl, Lukas
Rivinius, Marc
Bruhn, Andrés
author_facet Jahedi, Azin
Mehl, Lukas
Rivinius, Marc
Bruhn, Andrés
contents Many classical and learning-based optical flow methods rely on hierarchical concepts to improve both accuracy and robustness. However, one of the currently most successful approaches -- RAFT -- hardly exploits such concepts. In this work, we show that multi-scale ideas are still valuable. More precisely, using RAFT as a baseline, we propose a novel multi-scale neural network that combines several hierarchical concepts within a single estimation framework. These concepts include (i) a partially shared coarse-to-fine architecture, (ii) multi-scale features, (iii) a hierarchical cost volume and (iv) a multi-scale multi-iteration loss. Experiments on MPI Sintel and KITTI clearly demonstrate the benefits of our approach. They show not only substantial improvements compared to RAFT, but also state-of-the-art results -- in particular in non-occluded regions. Code will be available at https://github.com/cv-stuttgart/MS_RAFT.
format Preprint
id arxiv_https___arxiv_org_abs_2207_12163
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Multi-Scale RAFT: Combining Hierarchical Concepts for Learning-based Optical FLow Estimation
Jahedi, Azin
Mehl, Lukas
Rivinius, Marc
Bruhn, Andrés
Computer Vision and Pattern Recognition
Many classical and learning-based optical flow methods rely on hierarchical concepts to improve both accuracy and robustness. However, one of the currently most successful approaches -- RAFT -- hardly exploits such concepts. In this work, we show that multi-scale ideas are still valuable. More precisely, using RAFT as a baseline, we propose a novel multi-scale neural network that combines several hierarchical concepts within a single estimation framework. These concepts include (i) a partially shared coarse-to-fine architecture, (ii) multi-scale features, (iii) a hierarchical cost volume and (iv) a multi-scale multi-iteration loss. Experiments on MPI Sintel and KITTI clearly demonstrate the benefits of our approach. They show not only substantial improvements compared to RAFT, but also state-of-the-art results -- in particular in non-occluded regions. Code will be available at https://github.com/cv-stuttgart/MS_RAFT.
title Multi-Scale RAFT: Combining Hierarchical Concepts for Learning-based Optical FLow Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2207.12163