Papers › Cost Function Unrolling in Unsupervised Optical Flow

Cost Function Unrolling in Unsupervised Optical Flow

30 Nov 2020arXiv:2011.14814archive 2025-07-28

Gal Lifshitz, Dan Raviv

Steepest descent algorithms, which are commonly used in deep learning, use the gradient as the descent direction, either as-is or after a direction shift using preconditioning. In many scenarios calculating the gradient is numerically hard due to complex or non-differentiable cost functions, specifically next to singular points. In this work we focus on the derivation of the Total Variation semi-norm commonly used in unsupervised cost functions. Specifically, we derive a differentiable proxy to the hard L1 smoothness constraint in a novel iterative scheme which we refer to as Cost Unrolling. Producing more accurate gradients during training, our method enables finer predictions of a given DNN model through improved convergence, without modifying its architecture or increasing computational complexity. We demonstrate our method in the unsupervised optical flow task. Replacing the L1 smoothness constraint with our unrolled cost during the training of a well known baseline, we report improved results on both MPI Sintel and KITTI 2015 unsupervised optical flow benchmarks. Particularly, we report EPE reduced by up to 15.82% on occluded pixels, where the smoothness constraint is dominant, enabling the detection of much sharper motion edges.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

gallif/costfunctionunrolling officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Optical Flow EstimationRolling Shutter Correction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Optical Flow Estimation KITTI 2015 UnrolledCost Fl-all 10.81 #16 of 18 Archive leaderboard report
Optical Flow Estimation Sintel-clean UnrolledCost Average End-Point Error 4.69 #27 of 29 Archive leaderboard report
Optical Flow Estimation Sintel-final UnrolledCost Average End-Point Error 5.8 #26 of 28 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections