AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

Bowen Wen, Shaurya Dewan, Stan Birchfield

CVPR 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 14 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
distill hybrid FoundationStereo backbone priors into student backbone (ablation)Fast-FoundationStereo · Middlebury-HBP-2: 2.87 -> 2.20Improved
distill backbone priors (ablation)Fast-FoundationStereo · KITTI 2015D1: 4.32 -> 3.25Improved
MSE instead of cosine similarity distillation loss (ablation)Fast-FoundationStereo · Middlebury-HBP-2: 2.29 -> 2.20No clear effect
add pseudo-labeled in-the-wild data (ablation)Fast-FoundationStereo · Middlebury-HBP-2: 2.53 -> 2.20Improved
add pseudo-labeled data (ablation)LightStereo-L · ETH3DBP-1: 45.46 -> 21.12Improved
add pseudo-labeled data (ablation)RT-IGEV · KITTI 2015D1: 6.00 -> 4.40Improved
use blockwise NAS instead of random assembly under same latency budget (ablation)cost filtering module · Middlebury-Qzero-shot errorImproved
prune refinement module and retrain (ablation)refinement module · Middlebury-QaccuracyImproved
use Fast-FoundationStereo instead of FoundationStereoFoundationStereo · Middlebury-Qruntime (ms): 496 -> 49Improved
use Fast-FoundationStereo instead of FoundationStereoFoundationStereo · ETH3DBP-1: 0.50 -> 1.22Hurt

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