# Optical Flow in Mostly Rigid Scenes

## TL;DR

This paper introduces MR-Flow, an optical flow algorithm that combines static scene assumptions with moving object segmentation, improving accuracy in mostly rigid scenes by leveraging physical constraints and a Plane+Parallax framework.

## Contribution

It presents a novel method that explicitly segments moving objects and estimates scene structure and camera motion simultaneously, enhancing optical flow accuracy in mostly rigid scenes.

## Key findings

- Achieves state-of-the-art results on MPI-Sintel benchmark.
- Outperforms existing methods on KITTI-2015 dataset.
- Effectively combines static and dynamic scene modeling.

## Abstract

The optical flow of natural scenes is a combination of the motion of the observer and the independent motion of objects. Existing algorithms typically focus on either recovering motion and structure under the assumption of a purely static world or optical flow for general unconstrained scenes. We combine these approaches in an optical flow algorithm that estimates an explicit segmentation of moving objects from appearance and physical constraints. In static regions we take advantage of strong constraints to jointly estimate the camera motion and the 3D structure of the scene over multiple frames. This allows us to also regularize the structure instead of the motion. Our formulation uses a Plane+Parallax framework, which works even under small baselines, and reduces the motion estimation to a one-dimensional search problem, resulting in more accurate estimation. In moving regions the flow is treated as unconstrained, and computed with an existing optical flow method. The resulting Mostly-Rigid Flow (MR-Flow) method achieves state-of-the-art results on both the MPI-Sintel and KITTI-2015 benchmarks.