AI Paper Atlas

Research map / 3D vision / Depth and stereo

MonSter++: Unified Stereo Matching, Multi-View Stereo, and Real-Time Stereo With Monodepth Priors

Junda Cheng, Wenjing Liao, Zhipeng Cai, Longliang Liu, Gangwei Xu, Xianqi Wang, Yuzhou Wang, Zikang Yuan, Yong Deng, Jinliang Zang, Yangyang Shi, Jinhui Tang and 1 more

TPAMI 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo

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 Mono Guided Refinement instead of conv hourglass fusion (ablation)MonSter++ · Scene Flow testEPE: 6.52%Improved
add Stereo Guided Alignment for per-pixel scale and shift on top of MGR (ablation)MonSter++ · Scene Flow testEPE: 9.30% in EPE and 10.69% in 1-pixel errorImproved
use SGA instead of conv for shift refinement (ablation)MonSter++ · Scene Flow test1-pixel error: 8.09% improvement in 1-pixel errorImproved
add feature sharing of monocular ViT features with stereo branch (ablation)MonSter++ · Scene Flow testEPE: 0.39 -> 0.37Improved
add monocular branch with conv fusion to IGEV (ablation)IGEV · Scene Flow testEPE: 0.47 -> 0.46Improved
use DepthAnythingV2 instead of MiDaS as monocular branch (ablation)MonSter++ · Scene Flow testEPE: 0.41 -> 0.37Improved
use DepthAnythingV2 instead of DepthAnythingV1 as monocular branch (ablation)MonSter++ · Scene Flow testEPE: 0.39 -> 0.37Improved
reduce inference iterations from 32 to 4 (ablation)MonSter++ · Scene Flow testEPE: 0.37 -> 0.42Hurt
replace IGEV with MonSter++ using 4 iterations instead of 32MonSter++ vs IGEV · Scene Flow testEPE and run-time: 0.47 -> 0.42; 0.37s -> 0.34sImproved
add monocular prior fusion (MonSter++ over IGEV)IGEV · Zero-shot avg of 4 datasets (Scene Flow)error rate: 5.03 -> 3.70Improved
train on Full Training Set instead of Scene Flow onlyMonSter++ · Zero-shot avg of 4 datasetserror rate: 3.70 -> 2.30Improved
train on Full Training Set instead of Scene Flow onlyRT-MonSter++ · Zero-shot avg of 4 datasetserror rate: 7.03 -> 3.70Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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