AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching

Stepan Tulyakov, Anton Ivanov, François Fleuret

NeurIPS 2018 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 72 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
train on full-size 960 × 540 images instead of 512 × 256 patches (ablation)PDS · FlyingThings3D, test size 960 × 5403PE (%): 5.28 -> 4.50Improved
train on full-size 960 × 540 images instead of 512 × 256 patches (ablation)PDS · FlyingThings3D, test size 960 × 540MAE (px): 3.55 -> 3.40Improved
replace SoftArgmin with Sub-pixel MAP at inference (ablation)PDS trained with L1 loss · FlyingThings3D, disparity range [0, 255]3PE (%): 4.50 -> 4.22Improved
replace SoftArgmin with Sub-pixel MAP at inference (ablation)PDS trained with L1 loss · FlyingThings3D, disparity range [0, 255]MAE (px): 3.40 -> 3.42Hurt
extend the disparity range from [0, 255] to [0, 511] without retraining (ablation)PDS with SoftArgmin · FlyingThings3D3PE (%): 4.50 -> 5.20Hurt
extend the disparity range from [0, 255] to [0, 511] without retraining (ablation)PDS with Sub-pixel MAP · FlyingThings3D3PE (%): 4.22 -> 4.27No clear effect
train with sub-pixel cross-entropy instead of L1 loss (ablation)PDS with Sub-pixel MAP · FlyingThings3D, disparity range [0, 255]3PE (%): 4.22 -> 3.80Improved
train with sub-pixel cross-entropy instead of L1 loss (ablation)PDS with Sub-pixel MAP · FlyingThings3D, disparity range [0, 255]MAE (px): 3.42 -> 3.63Hurt

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