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

PatchBatch: a Batch Augmented Loss for Optical Flow

About

We propose a new pipeline for optical flow computation, based on Deep Learning techniques. We suggest using a Siamese CNN to independently, and in parallel, compute the descriptors of both images. The learned descriptors are then compared efficiently using the L2 norm and do not require network processing of patch pairs. The success of the method is based on an innovative loss function that computes higher moments of the loss distributions for each training batch. Combined with an Approximate Nearest Neighbor patch matching method and a flow interpolation technique, state of the art performance is obtained on the most challenging and competitive optical flow benchmarks.

David Gadot, Lior Wolf• 2015

Related benchmarks

TaskDatasetResultRank
Optical FlowMPI Sintel Clean (test)
AEE5.79
158
Optical FlowMPI-Sintel final (test)
EPE6.78
137
Optical FlowKITTI 2012 (train)
AEE3.3
115
Optical FlowKITTI-15 (test)
Fl-all21.07
85
Optical Flow EstimationKITTI 2012 (test)
AEE3.3
41
Showing 5 of 5 rows

Other info

Follow for update