An Analysis and Speedup of the FALDOI Method for Optical Flow Estimation
Ferran P. Gamonal, Coloma Ballester, Gloria Haro, Enric Meinhardt-Llopis, Roberto P. Palomares
published
2019-03-08
reference
Ferran P. Gamonal, Coloma Ballester, Gloria Haro, Enric Meinhardt-Llopis, and Roberto P. Palomares, An Analysis and Speedup of the FALDOI Method for Optical Flow Estimation, Image Processing On Line, 9 (2019), pp. 94–123. https://doi.org/10.5201/ipol.2019.238

Communicated by Luis Álvarez and Jose-Luis Lisani
Demo edited by Jose-Luis Lisani

Abstract

We present a detailed analysis of FALDOI, a large displacement optical flow method proposed by P.Palomares et al. This method requires a set of discrete matches, which can be extremely sparse, and an energy functional which locally guides the interpolation from the matches. It follows a two-step minimization method at the finest scale which is very robust to the outliers of the sparse matcher and can capture large displacements of small objects. The results shown in the original paper consistently outperformed the coarse-to-fine approaches and achieved good qualitative and quantitative performance on the standard optical flow benchmarks. In this paper we revise the proposed method and the changes done to significantly reduce its execution time while reporting nearly the same accuracy. Finally, we also compare it against the current state-of-the-art to assess its performance.

Download

Non-Reviewed Supplementary Materials

These files and information are provided by the authors and have not been reviewed.

CONTENTS:

- All the images shown in the article and some extra ones ('more_example_data').
- Evaluation code used to computed the EPE_all, EPE_mat, etc. (see MPI Sintel Dataset for all the metrics).
- Visualization code to create a png file from a flo file (with the Middlebury colour coding).  
- All the article resulting 'flo' files (ordered in a per-figure basis).

History