AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Bilateral Grid Learning for Stereo Matching Networks

Bin Xu, Yuhua Xu, Xiaoli Yang, Wei Jia, Yulan Guo

CVPR 2021 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 142 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 linear cost-volume upsampling with CUBG (ablation)BGNet · SceneFlow FinalpassEPE: 1.40 -> 1.17Improved
Replace linear cost-volume upsampling with CUBG (ablation)BGNet · SceneFlow Finalpass, edge regionsEPE-edge: 8.13 -> 5.95Improved
Replace linear cost-volume upsampling with CUBG (ablation)BGNet · SceneFlow Finalpass, flat regionsEPE-flat: 0.71 -> 0.68No clear effect
Replace the learned guidance map with input-image luma (ablation)BGNet CUBG · SceneFlowEPE: 1.17 -> 1.28Hurt
Build the cost volume at 1/16 rather than the original resolution (ablation)BGNet · SceneFlowEPE: 1.17 -> 1.58Hurt
Build the cost volume at 1/16 rather than the original resolution (ablation)BGNet · SceneFlowruntime (ms): 25.3 ms to 17.1 msImproved
Embed CUBG cost-volume upsamplingGCNet · SceneFlowEPE: 2.51 -> 1.07Improved
Embed CUBG cost-volume upsamplingPSMNet · SceneFlowEPE: 1.09 -> 0.92Improved
Embed CUBG cost-volume upsamplingGANet_deep · SceneFlowEPE: 0.95 -> 0.63Improved
Embed CUBG and replace the narrow-volume pipeline with full-volume aggregationDeepPrunerFast · SceneFlowEPE: 0.97 -> 0.84Improved
Add an hourglass disparity refinement module (ablation)BGNet · KITTI 2015 testD1-all: 2.51 -> 2.19Improved
Train with IRS in addition to Flyingthings3DBGNet and BGNet+ · Middlebury 2014Bad 2.0 (%): 17.5 -> 13.5; 17.2 -> 11.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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