AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

The Domain Transform Solver

Akash Bapat, Jan-Michael Frahm

CVPR 2019 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 7 citations (OpenAlex)

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
Replace BL-Solver refinement with DTSMC-CNN stereo refinement · Middlebury trainingtime/MP (s): 42.7 (126) -> 5.9 (89.2)Improved
Replace BL-Solver refinement with DTSMC-CNN stereo refinement · Middlebury trainingMAE (px), non-occluded: 2.60 -> 3.02Hurt
Replace BL-Solver refinement with DTSMC-CNN stereo refinement · Middlebury testingtime/MP (s): 28 (140) -> 10 (122)Improved
Replace BL-Solver refinement with DTSMC-CNN stereo refinement · Middlebury testingMAE (px), non-occluded: 2.67 -> 3.78Hurt
Use DTS instead of bicubic upsampling aloneDepth super-resolution · Art/Books/Moebius averageAvg. error (px): 5.94 -> 3.43Improved
Replace BL-Solver with DTSDepth super-resolution · Art/Books/Moebius averageAvg. error (px): 2.75 -> 3.43Hurt
Replace BL-Solver with DTSDepth super-resolution · Art/Books/Moebius averagetime (s): 0.234 -> 0.0215Improved
Increase gradient-descent iterationsDTS stereo optimization · Middlebury trainingMAE and RMSEImproved

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