Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss

About

In the era of end-to-end deep learning, many advances in computer vision are driven by large amounts of labeled data. In the optical flow setting, however, obtaining dense per-pixel ground truth for real scenes is difficult and thus such data is rare. Therefore, recent end-to-end convolutional networks for optical flow rely on synthetic datasets for supervision, but the domain mismatch between training and test scenarios continues to be a challenge. Inspired by classical energy-based optical flow methods, we design an unsupervised loss based on occlusion-aware bidirectional flow estimation and the robust census transform to circumvent the need for ground truth flow. On the KITTI benchmarks, our unsupervised approach outperforms previous unsupervised deep networks by a large margin, and is even more accurate than similar supervised methods trained on synthetic datasets alone. By optionally fine-tuning on the KITTI training data, our method achieves competitive optical flow accuracy on the KITTI 2012 and 2015 benchmarks, thus in addition enabling generic pre-training of supervised networks for datasets with limited amounts of ground truth.

Simon Meister, Junhwa Hur, Stefan Roth• 2017

Related benchmarks

TaskDatasetResultRank
Optical Flow EstimationKITTI 2015 (train)
Fl-epe8.1
431
Optical Flow EstimationMPI Sintel Final (train)
Endpoint Error (EPE)7.91
209
Optical FlowMPI Sintel Clean (test)
AEE9.38
158
Optical FlowMPI-Sintel final (test)
EPE7.91
137
Optical FlowKITTI 2012 (train)--
115
Optical Flow EstimationSintel clean (test)
EPE9.38
103
Optical Flow EstimationSintel Final (test)
EPE10.21
101
Optical FlowKITTI 2015 (test)
Fl Error (All)11.11
95
Optical FlowSintel Final (train)
EPE7.91
92
Optical Flow EstimationKITTI 2015 (test)
Fl-all23.3
91
Showing 10 of 13 rows

Other info

Follow for update