AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

A Lightweight Optical Flow CNN —Revisiting Data Fidelity and Regularization

Tak-Wai Hui, Xiaoou Tang, Chen Change Loy

TPAMI 2020 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 225 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
use extra training loss, lr 6e-5, and LiteFlowNet2 changes instead of LiteFlowNet (Chairs)LiteFlowNet · KITTI 2012 (Chairs-trained)AEE: 4.73 -> 4.11Improved
raise learning rate from 5e-5 to 6e-5 (ablation)LiteFlowNet2 · KITTI 2015 (Chairs-trained)AEE: 12.01 -> 11.76Improved
add extra training loss at upsampled final flow (ablation)LiteFlowNet2 · KITTI 2015 (Chairs-trained)AEE: 11.76 -> 11.31Improved
add pyramid level 2 to NetE (level 3 -> level 2) (ablation)LiteFlowNet · Sintel Clean (train)AEE: 2.65 -> 2.48No clear effect
add pyramid level 2 to NetE (ablation)LiteFlowNet · Sintel runtimeruntime (ms): 13.06 -> 52.51Hurt
add pseudo flow inference and regularization at level 2 (ablation)LiteFlowNet2 · Sintel runtimeruntime (ms): 52.51ms to 8.95msImproved
add pseudo network at level 2 (ablation)LiteFlowNet2 · Sintel testing setAEENo clear effect
add pseudo network at level 2 (ablation)LiteFlowNet2 · KITTI testing setAEEImproved
fine-tune on Sintel+KITTI mixture instead of Sintel only (ablation)LiteFlowNet2-ft · Sintel Clean (test)AEE: 3.83 -> 3.48Improved
fine-tune on Sintel+KITTI mixture instead of Sintel only (ablation)LiteFlowNet2-ft · Sintel Final (test)AEE: 5.06 -> 4.69Improved
train LiteFlowNet with new fine-tuning protocol (ablation)LiteFlowNet-ft · Sintel Clean (test)AEE: 4.54 -> 4.01Improved
train LiteFlowNet with new fine-tuning protocol (ablation)LiteFlowNet-ft · Sintel Final (test)AEE: 5.38 -> 5.21Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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