AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Improving Optical Flow on a Pyramid Level

Markus Hofinger, Samuel Rota Bulò, Lorenzo Porzi, Arno Knapitsch, Thomas Pock, Peter Kontschieder

ECCV 2020 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling · 45 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add gradient stopping between pyramid levels (ablation)HD3 re-trained · Flying Chairs2 valEPE: 1.422 -> 1.215Improved
add flow cues on top of gradient stopping and sampling (ablation)HD3 with gradient stopping + sampling · Flying Chairs2 valEPE: 1.208 -> 1.186Improved
add flow cues on top of gradient stopping with warping (ablation)HD3 with gradient stopping, warping · Flying Chairs2 valEPE: 1.215 -> 1.216No clear effect
add loss max-pooling to the full model (ablation)HD3 with all other contributions · Flying Chairs2 valFl-all (%): 6.15 -> 5.97Improved
add SAD distance on top of sampling and flow cues (ablation)HD3 with gradient stopping, sampling, cues · Flying Things val (trained on Flying Chairs2)EPE: 19.616 -> 15.136Improved
add LMP to gradient stopping alone (no sampling, cues or SAD) (ablation)HD3 with gradient stopping · Sintel final train (trained on Flying Chairs2)EPE: 5.774 -> 12.529Hurt
add cost volume sampling on top of gradient stopping (ablation)HD3 with gradient stopping · Flying Things val (trained on Flying Chairs2)Fl-all (%): 26.84 -> 24.75Improved
extend cost volume range from +-4 to +-8 with sampling and LMP (ablation)HD3 sampling + LMP · Flying Chairs2 valEPE: 0.06Improved
extend cost volume range from +-4 to +-8 with sampling, no LMP (ablation)HD3 sampling · Flying Chairs2 valEPE: 0.01No clear effect
add knowledge distillation to KITTI fine-tuning (ablation)IOFPL-CVr8 · KITTI 2015 trainFl-all (%): 3.58 -> 3.28Improved
add knowledge distillation to KITTI fine-tuning (generalization) (ablation)IOFPL-CVr8 · Flying Things valFl-all (%): 46.2 -> 38.0Improved
add gradient stopping at the upsampling layer (ablation)PWC-Net (IRR-PWC code) on Flying Chairs · Flying Chairs valEPE: 10% at 20 epochs, 6% at 100 epochsImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy