AI Paper Atlas

Research map / 3D vision / Depth and stereo

SPE-MVS: Spatial Position Encoding Enhanced Multi-View Stereo with Monocular Depth Priors

Shaoqian Wang, Jiadai Sun, Bosen Hou, Qiang Wang, Bin Fan, Bo Li, Bin Lu, Yuchao Dai

CVPR 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 PSHF hybrid feature extractor (ablation)SPE-MVS baseline skeleton · DTUOverall (mm): 0.298 -> 0.283Improved
add SPEC spatial-position cost volume (ablation)SPE-MVS baseline skeleton · DTUOverall (mm): 0.298 -> 0.288Improved
add MDGE module (ablation)SPE-MVS baseline skeleton · DTUOverall (mm): 0.298 -> 0.286Improved
add all of PSHF, SPEC and MDGE (ablation)SPE-MVS baseline skeleton · DTUOverall (mm): 0.298 -> 0.272Improved
dual-branch fusion extractor instead of input concatenation (ablation)PSHF · DTUOverall (mm): 0.277 -> 0.272Improved
dual-branch fusion extractor instead of dual-encoder (ablation)PSHF · DTUOverall (mm): 0.276 -> 0.272Improved
use MFE and MDE together instead of MFE only (ablation)MDGE · DTUOverall (mm): 0.274 -> 0.272Improved
remove monocular feature prior from MFE (ablation)MDGE · DTUOverall (mm): 0.274 -> 0.277Hurt
remove monocular depth prior from MDE (ablation)MDGE · DTUOverall (mm): 0.276 -> 0.278Hurt
add MDGE module increases cost (ablation)SPE-MVS · DTUtime per view (s): 0.42 -> 0.58Hurt
replace MonoMVSNet with SPE-MVSMonoMVSNet · DTUCompleteness (mm): 0.243 -> 0.220Improved
replace MonoMVSNet with SPE-MVSMonoMVSNet · DTUAccuracy (mm): 0.313 -> 0.324Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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