AI Paper Atlas

Research map / 3D vision / Depth and stereo

EC-MVSNet: Enhanced Cascaded Multi-View Stereo with Cross-Scale Relevance Integration

Shaoqian Wang, Jiadai Sun, Bin Fan, Qiang Wang, Bin Lu, Yuchao Dai

AAAI 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 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 CFC joint cross-scale cost volume (ablation)cascade MVS baseline · DTU testOverall (mm): 0.303 -> 0.290Improved
add CPE probability-guided enhancement (ablation)cascade MVS baseline · DTU testOverall (mm): 0.303 -> 0.284Improved
add MFR monocular refinement (ablation)cascade MVS baseline · DTU testOverall (mm): 0.303 -> 0.288Improved
add CPE on top of CFC (ablation)cascade MVS baseline · DTU testOverall (mm): 0.290 -> 0.279Improved
add MFR on top of CFC+CPE (ablation)cascade MVS baseline · DTU testOverall (mm): 0.279 -> 0.275Improved
aggregate adjacent higher-scale features instead of lower (ablation)cascade MVS baseline · DTU testOverall (mm): 0.275 -> 0.278Hurt
aggregate both higher and lower scale features in CFC (ablation)cascade MVS baseline · DTU testOverall (mm): 0.275 -> 0.274No clear effect
aggregate features from all scales in CFC (ablation)cascade MVS baseline · DTU testOverall (mm): 0.275 -> 0.274No clear effect
use EC-MVSNet instead of MVSFormer++ (ablation)cascade MVS baseline · DTU testCompleteness (mm): 0.252 -> 0.253Hurt
use EC-MVSNet instead of RRT-MVSEC-MVSNet · Tanks and Temples Intermediatemean F1: 68.16 -> 69.32Improved
use EC-MVSNet instead of RRT-MVSEC-MVSNet · Tanks and Temples Advancedmean F1: 43.29 -> 44.63Improved
use EC-MVSNet instead of GoMVSEC-MVSNet · ETH3D TestingRecall: 86.85 -> 84.53Hurt

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