AI Paper Atlas

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

PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts

Xianqi Wang, Hao Yang, Hangtian Wang, Junda Cheng, Gangwei Xu, Min Lin, Xin Yang

CVPR 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 4 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
replace dual-branch GRU with Prompt Recurrent Unit plus motion prompt (ablation)MonSter · Midd-T Bad 2.0Bad 2.0 (%): 7.27 -> 4.18Improved
add Structure Prompt (ablation)PRU + MP · Midd-T Bad 2.0Bad 2.0 (%): 4.18 -> 3.90Improved
add Affine-Invariant Fusion of initial disparity and relative depth (ablation)PRU + MP + SP · Midd-T Bad 2.0Bad 2.0 (%): 3.90 -> 3.76Improved
replace GRU with PRU in RAFT-Stereo (ablation)RAFT-Stereo · KITTI 2015 Bad 3.0Bad 3.0 (%): 5.68 -> 4.78Improved
replace GRU with PRU in IGEV-Stereo (ablation)IGEV-Stereo · KITTI 2015 Bad 3.0Bad 3.0 (%): 6.03 -> 4.84Improved
remove pre-trained DPT decoder weights from PRU (ablation)PromptStereo · Midd-T Bad 2.0Bad 2.0 (%): 4.39 -> 3.76Improved
merge hidden state and prompt into one conv block (ablation)PromptStereo · Midd-T Bad 2.0Bad 2.0 (%): 3.76 -> 4.37Hurt
use zero-initialized last conv in prompt block (ablation)PromptStereo · Midd-T Bad 2.0Bad 2.0 (%): 3.76 -> 4.04Hurt
use PRU instead of GRU at 4 iterations (ablation)PromptStereo vs MonSter · Midd-2021 Bad 2.0Bad 2.0 (%): 10.75 -> 4.35Improved
increase inference iterations from 16 to 32 (ablation)PromptStereo · Midd-2021 Bad 2.0Bad 2.0 (%): 2.79 -> 2.78No clear effect
increase inference iterations from 16 to 32 (ablation)PromptStereo · Booster (Q) Bad 2.0Bad 2.0 (%): 4.09 -> 3.67Improved
train on unlimited mixed datasets instead of Scene Flow onlyPromptStereo · Booster (Q) Bad 2.0Bad 2.0 (%): 12.13 -> 3.67Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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