AI Paper Atlas

Research map / Architectures and efficiency / Mixture of experts

Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts

Yun Wang, Longguang Wang, Chenghao Zhang, Yongjian Zhang, Zhanjie Zhang, Ao Ma, Chenyou Fan, Tin Lun Lam, Junjie Hu

ICCV 2025 · Architectures and efficiency › Mixture of experts · approach: Sparse MoE as regularization and attention · 22 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 MoE LoRA and MoE Adapter to the frozen VFM (ablation)SMoEStereo (DAMV2 ViT-base) · KITTI 2015 (RVC ablation)D1_All: 2.01 -> 1.57Improved
add MoE LoRA alone (ablation)SMoEStereo (DAMV2 ViT-base) · Middlebury (RVC ablation)Bad 2.0: 7.67 -> 4.80Improved
add MoE Adapter alone (ablation)SMoEStereo (DAMV2 ViT-base) · Middlebury (RVC ablation)Bad 2.0: 7.67 -> 4.68Improved
add the learned decision network to prune MoE modules (ablation)SMoEStereo (DAMV2 ViT-base) · KITTI 2015 (RVC ablation)D1_All and extra params: 1.57 -> 1.51; params 6.77 -> 2.86Improved
replace learned usage policy with a random policy of similar cost (ablation)SMoEStereo (DAMV2 ViT-base) · KITTI 2015 (RVC ablation)D1_All: 1.51 -> 1.69Hurt
use mixed-rank MoE LoRA experts instead of homogeneous fixed rank 4 (ablation)SMoE MoE LoRA · KITTI 2015 (RVC ablation)D1_All: 1.77 -> 1.51Improved
use sparse expert selection instead of aggregating all experts (Multi-E) (ablation)SMoEStereo · Middlebury (RVC ablation)Bad 2.0: 4.37 -> 4.12Improved
use sparse expert selection instead of Multi-E on KITTI 2015 (ablation)SMoEStereo · KITTI 2015 (RVC ablation)D1_All: 1.46 -> 1.51Hurt
selective activation instead of all experts for speed (ablation)SMoEStereo · KITTI inference speedinference speed: 4.68 iter/s -> 5.26 iter/sImproved
use SMoE instead of LoRA for adapting DAMV2DAMV2 ViT-base · Middlebury zero-shotBad 2.0: 7.67 -> 7.05Improved
use PEFT (LoRA) instead of full fine-tuningDAMV2 ViT-base · KITTI 2015 zero-shotBad 3.0: 14.3 -> 5.03Improved
scale VFM capacity from ViT-Small to ViT-LargeSMoEStereo (DAMV2) · ETH3D zero-shotBad 1.0: 2.43 -> 1.87Improved

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