AI Paper Atlas

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

Lite Any Stereo: Efficient Zero-Shot Stereo Matching

Junpeng Jing, Weixun Luo, Ye Mao, Krystian Mikolajczyk

CVPR 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 1 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
use hybrid 3D-then-2D cost aggregation instead of 2D only (ablation)Lite Any Stereo · ETH3D (1.4M synthetic subset)Bad 1.0: 6.48 -> 5.39 (2D vs 3D-2D); KITTI 2012 5.02 -> 4.78Mixed
place the 2D block before the 3D block (ablation)Lite Any Stereo cost aggregation · ETH3D (1.4M synthetic subset)Bad 1.0: 5.39 -> 28.85Hurt
enlarge the 3D kernel along the disparity dimension (ablation)Lite Any Stereo cost aggregation · KITTI 2012 (1.4M synthetic subset)D1: 4.38 -> 4.86 (kernel (11,3,3))Hurt
increase 3D block proportion beyond 4.8% (ablation)Lite Any Stereo cost aggregation · Middlebury (1.4M synthetic subset)Bad 2.0: 9.50 -> 10.34 (15.6%)Hurt
use ConvNeXt layers instead of MobileNetV2 in the 2D block (ablation)Lite Any Stereo · KITTI 2012 (1.4M synthetic subset)D1: 4.78 -> 4.38; MACs 33.9 -> 32.8Improved
add self-distillation stage rather than direct data augmentation (ablation)Lite Any Stereo · Middlebury (1.4M synthetic subset)Bad 2.0: 11.14 (data aug.) -> 8.86 (know. dis.)Improved
update teacher via EMA or hard copy instead of fixed teacher (ablation)Stage 2 self-distillation · KITTI 2012 (1.4M synthetic subset)D1: 3.64 -> 3.97 (EMA), 4.22 (hard copy)Hurt
add stage 3 real-world pseudo-label distillation after stage 2 (ablation)Lite Any Stereo · ETH3D (full training set)Bad 1.0: 4.69 -> 3.53Improved
add stage 3 on real-world data (ablation)Lite Any Stereo · Middlebury (full training set)Bad 2.0: 7.03 -> 7.51Hurt
apply the three-stage training strategy to other efficient architecturesLightStereo-M · KITTI 2012D1: 4.34 -> 3.35Improved
apply the three-stage training strategy to BANet-2DBANet-2D · MiddleburyBad 2.0: 10.54 -> 10.30 (stage 3); KITTI 2012 4.34 -> 3.28Mixed
add low-quality or domain-specific data (e.g. Stereo4D, HRWSI) in stage 3Lite Any Stereo · zero-shot benchmarkszero-shot accuracyHurt

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