AI Paper Atlas

Research map / 3D vision / Depth and stereo

MVSCRF: Learning Multi-View Stereo With Conditional Random Fields

Youze Xue, Jiansheng Chen, Weitao Wan, Yiqing Huang, Cheng Yu, Tianpeng Li, Jiayu Bao

ICCV 2019 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 111 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 U-shape feature extractor (ablation)MVSNet · DTUaccuracy distance (mm): 0.396 -> 0.351Improved
add U-shape feature extractor (ablation)MVSNet · DTUoverall mean distance (mm): 0.462 -> 0.432Improved
add U-shape feature extractor (ablation)MVSNet · DTUcompleteness distance (mm): 0.527 -> 0.513Improved
add multi-scale CRFs module on top of U-extractor (ablation)MVSNet + U-extractor · DTUcompleteness distance (mm): 0.513 -> 0.426Improved
add multi-scale CRFs module on top of U-extractor (ablation)MVSNet + U-extractor · DTUoverall mean distance (mm): 0.432 -> 0.398Improved
add multi-scale CRFs module on top of U-extractor (ablation)MVSNet + U-extractor · DTUaccuracy distance (mm): 0.351 -> 0.371Hurt
use multi-scale CRF instead of single-scale CRF (ablation)MVSCRF · Tanks and Templesmean f-score: 44.00 -> 45.73Improved
use multi-scale CRF instead of single-scale CRF (ablation)MVSCRF · DTU (<1mm)f-score (%): 79.77 -> 80.02No clear effect
add MVSCRF components instead of denser depth sampling (256 vs 512 samples) (ablation)R-MVSNet · DTUoverall mean distance (mm): 0.417 -> 0.398Improved
add post-processing and fusibile fusion to reproduced MVSNetMVSNet · DTUmean distance (mm): 0.462 -> 0.462No clear effect

Later papers that compared with this method

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

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