AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Pseudo-Stereo Inputs: A Solution to the Occlusion Challenge in Self-Supervised Stereo Matching

Ruizhi Yang, Xingqiang Li, Jiajun Bai, Jinsong Du

ECCV 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 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
add pseudo-stereo inputs strategyPSMNet · SceneFlow3-px error (%): 16.85 -> 9.80Improved
add pseudo-stereo inputs strategyMonSter · SceneFlowEPE (px): 5.28 -> 2.32Improved
add pseudo-stereo inputs strategyGMStereo · SceneFlow3-px error (%): 15.01 -> 8.49Improved
add pseudo-stereo inputs strategyPSMNet · Spring (half res)EPE (px): 2.41 -> 2.30Improved
add pseudo-stereo inputs strategyMonSter · Spring (half res)3-px error (%): 6.56 -> 4.65Improved
add pseudo-stereo inputs alone (ablation)baseline self-supervised stereo · KITTI 2015 trainD1 (%): 5.67 -> 4.99Improved
add occlusion estimation alone (ablation)baseline self-supervised stereo · KITTI 2015 trainD1 (%): 5.67 -> 5.73Hurt
add occlusion estimation to pseudo-stereo inputs (ablation)Pseudo-Stereo · KITTI 2015 trainD1 (%): 4.99 -> 4.08Improved
add fully pseudo-stereo inputs strategy to PS and Occ (ablation)Pseudo-Stereo · KITTI 2015 trainD1 (%): 4.08 -> 4.31Hurt
add fully pseudo-stereo inputs strategy to PS (ablation)Pseudo-Stereo · KITTI 2015 trainD1 (%): 4.99 -> 5.17Hurt
add refined pseudo-image generation (ablation)Pseudo-Stereo with FPS · KITTI 2015 trainD1 (%): 4.31 -> 4.06Improved
add refined pseudo-image generation (ablation)Pseudo-Stereo with FPS · KITTI 2015 trainEPE (px): 1.04 -> 1.01Improved

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