AI Paper Atlas

Research map / 3D vision / Depth and stereo

Hierarchical Prior Mining for Non-local Multi-View Stereo

Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang

ICCV 2023 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 20 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 non-local sampling (NSP) to the ACMH baseline (ablation)ACMH · ETH3D train, 1cmF1 (%): 61.71 -> 63.84Improved
add extensible sampling (ESP) to the ACMH baseline (ablation)ACMH · ETH3D train, 1cmF1 (%): 61.71 -> 62.22Improved
combine non-local and extensible sampling (NESP) (ablation)ACMH · ETH3D train, 1cmF1 (%): 61.71 -> 64.22Improved
add planar prior assistance on top of NESP (ablation)NESP · ETH3D train, 1cmF1 (%): 64.22 -> 71.32Improved
add hierarchical prior mining (multi-scale priors) on top of NESP and planar prior (ablation)HPM-MVS · ETH3D train, 10cmF1 (%): 92.73 -> 96.22Improved
use full hierarchical prior instead of coarsest-scale only (fast version) (ablation)HPM-MVS · ETH3D train, 1cmF1 (%): 67.39 -> 72.73Improved
plug NESP into ACMM (ablation)ACMM · ETH3D train, 1cmF1 (%): 67.58 -> 70.70Improved
plug NESP into ACMP (ablation)ACMP · ETH3D train, 1cmF1 (%): 68.72 -> 70.87Improved
plug NESP into ACMMP (ablation)ACMMP · ETH3D train, 1cmF1 (%): 71.57 -> 74.54Improved
plug NESP into ACMM at 20cm threshold (ablation)ACMM · ETH3D train, 20cmF1 (%): 94.41 -> 94.55Improved
use HPM-MVS on Tanks & Temples Advanced without fine-tuningHPM-MVS · Tanks & Temples AdvancedF1 (%): 37.84 -> 40.80Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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