[Paper] [Supplementary] [Code]

We guide a deep optical flow network with external hints, in order to increase its accuracy.

Abstract. This paper proposes a framework to guide an optical flow network with external cues to achieve superior accuracy either on known or unseen domains. Given the availability of sparse yet accurate optical flow hints from an external source, these are injected to modulate the correlation scores computed by a state-of-the-art optical flow network and guide it towards more accurate predictions. Although no real sensor can provide sparse flow hints, we show how these can be obtained by combining depth measurements from active sensors with geometry and hand-crafted optical flow algorithms, leading to accurate enough hints for our purpose. Experimental results with a state-of-the-art flow network on standard benchmarks support the effectiveness of our framework, both in simulated and real conditions.

Given a depth sensor (e.g., a LiDAR), we obtain accurate flow hints used to guide a deep optical flow network. Hints are obtained by combining the ego-motion flow (consequence of depth and estimated camera poses) and flow values estimated by a hand-crafted method (RICFlow).

Citation:

@inproceedings{Poggi_ICCV_2021,
title     = {Sensor-Guided Optical Flow},
author    = {Poggi, Matteo and
            Aleotti, Filippo and
            Mattoccia, Stefano},
booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
year = {2021}
}