AI Paper Atlas

Research map / 3D vision / Depth and stereo

MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network

Jianfei Jiang, Qiankun Liu, Haochen Yu, Hongyuan Liu, Liyong Wang, Jiansheng Chen, Huimin Ma

ICCV 2025 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 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
add reference monocular feature (ablation)MonoMVSNet · DTUOverall: 0.303 -> 0.293Improved
add reference monocular feature (ablation)MonoMVSNet · DTUCompleteness: 0.282 -> 0.263Improved
add cross attention to monocular features (ablation)MonoMVSNet · DTUOverall: 0.293 -> 0.293No clear effect
add cross-view positional encoding (ablation)MonoMVSNet · DTUOverall: 0.293 -> 0.288Improved
add monocular guided depth sampling (ablation)MonoMVSNet · DTUOverall: 0.288 -> 0.292Hurt
add edge map to depth sampling (ablation)MonoMVSNet · DTUOverall: 0.292 -> 0.283Improved
add relative consistency loss (ablation)MonoMVSNet · DTUOverall: 0.283 -> 0.281Improved
extract monocular features from reference view only instead of all views (ablation)MonoMVSNet · DTUOverall: 0.297 -> 0.284Improved
extract monocular features from reference view only instead of all views (ablation)MonoMVSNet · DTUMemory: 5.72GB -> 2.01GBImproved
replace 2D PE+MLP with CVPE (ablation)MonoMVSNet · DTUOverall: 0.285 -> 0.278Improved
use larger ViT-L instead of ViT-S (ablation)MonoMVSNet · DTUOverall: 0.278 -> 0.281No clear effect
use Depth Anything V2 instead of Depth Pro (ablation)MonoMVSNet · DTUOverall: 0.286 -> 0.278Improved

Later papers that compared with this method

1 later accepted paper reports MonoMVSNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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