AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

LSM: Learning Subspace Minimization for Low-Level Vision

Chengzhou Tang, Lu Yuan, Ping Tan

CVPR 2020 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 18 citations (OpenAlex)

Check 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 LSM trained on the other three tasks instead of PWC-Net for zero-shot stereo matchingZero-shot stereo matching · FlyingThings3DEPE: 5.29 -> 2.47Improved
Train LSM on the other three tasks and apply it zero-shot to optical flowLSM · SintelEPE: 4.6 EPEImproved
Train LSM on the other tasks and apply it zero-shot to video segmentationLSM · DAVIS-2016IoU: 0.682 IoUMixed
Replace explicit minimization with a CNN implicit solver that predicts the solution (ablation)LSM · Interactive segmentationIoUHurt
Replace explicit minimization with a CNN implicit solver that predicts the solution (ablation)LSM · Video segmentationIoUHurt
Replace explicit minimization with a CNN implicit solver that predicts the solution (ablation)LSM · Stereo matchingEPEHurt
Replace explicit minimization with a CNN implicit solver that predicts the solution (ablation)LSM · Optical flowEPEHurt
Remove minimization context from subspace generation (ablation)LSM · Interactive segmentation, video segmentation, stereo matching, and optical flowTask performanceHurt
Remove subspace projection during minimization (ablation)LSM · Interactive segmentation, video segmentation, stereo matching, and optical flowTask performanceHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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