AI Paper Atlas

Research map / 3D vision / Depth and stereo

EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo

Xinjun Ma, Yue Gong, Qirui Wang, Jingwei Huang, Lei Chen, Fan Yu

ICCV 2021 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 157 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 epipolar-assembling module at the same depth number of 32 (ablation)EPP-MVSNet 1st stage · DTU evaluationoverall error (mm): 0.7049 -> 0.5920Improved
add epipolar-assembling instead of raising depth number to 96 (ablation)EPP-MVSNet 1st stage · DTU evaluationoverall error (mm): 0.6282 -> 0.5920Improved
add epipolar-assembling instead of raising depth number to 160 (ablation)EPP-MVSNet 1st stage · DTU evaluationoverall error (mm): 0.6298 -> 0.5920Improved
use max pooling instead of average pooling in assembling kernel (ablation)EAM kernel · DTU evaluationoverall error (mm): 0.5994 -> 0.5920Improved
use 3x1x1 convolution kernel instead of 1x1x1 (ablation)EAM kernel · DTU evaluationoverall error (mm): 0.7163 -> 0.5920Improved
use 5x1x1 kernel instead of 3x1x1 (ablation)EAM kernel · DTU evaluationoverall error (mm): 0.5920 -> 0.5921No clear effect
add entropy-based refining strategy (ablation)EPP-MVSNet 3rd stage · DTU evaluationoverall error (mm): 0.3595 -> 0.3553Improved
replace 3D CNN with Pseudo-3D CNN in regularization (ablation)EPP-MVSNet · DTU evaluationoverall error (mm): 0.3575 -> 0.3553No clear effect
replace 3D CNN with Pseudo-3D CNN in regularization (ablation)EPP-MVSNet · DTU evaluationtime (ms): 624.9 -> 340.6Improved
replace 3D CNN with Pseudo-3D CNN in regularization (ablation)EPP-MVSNet · DTU evaluationmemory (GB): 5.2 -> 3.1Improved
replace 3D block with Pseudo-3D block on 32x296x400 volume (ablation)regularization block · DTU evaluationrun-time (ms): 23.6 -> 16.4Improved
replace 3D block with Pseudo-3D block on 64x296x400 volume (ablation)regularization block · DTU evaluationrun-time (ms): 46.6 -> 31.7Improved

Later papers that compared with this method

5 later accepted papers report EPP-MVSNet as a baseline in their results tables; 4 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 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