AI Paper Atlas

Research map / 3D vision / Depth and stereo

Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation

Hongwei Yi, Zizhuang Wei, Mingyu Ding, Runze Zhang, Yisong Chen, Guoping Wang, Yu-Wing Tai

ECCV 2020 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 144 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 pixel-wise view aggregation (ablation)MVSNet-style baseline · DTU evaluationaccuracy error (mm): 0.454 -> 0.390Improved
add voxel-wise view aggregation (ablation)MVSNet-style baseline · DTU evaluationaccuracy error (mm): 0.454 -> 0.378Improved
use voxel-wise instead of pixel-wise aggregation (ablation)VA-MVSNet · DTU evaluationoverall error (mm): 0.379 -> 0.369Improved
add multi-metric pyramid depth aggregation (MMP) (ablation)VA-MVSNet with VoxelVA · DTU evaluationcompleteness error (mm): 0.359 -> 0.336Improved
add multi-metric pyramid depth aggregation (MMP) (ablation)VA-MVSNet with VoxelVA · DTU evaluationaccuracy error (mm): 0.378 -> 0.379Hurt
add multi-metric pyramid depth aggregation (MMP) (ablation)VA-MVSNet with PixelVA · DTU evaluationoverall error (mm): 0.379 -> 0.366Improved
increase test views from 2 to 5VA-MVSNet trained on 3 views · DTU evaluationoverall error (mm): 0.441 -> 0.371Improved
increase test views from 5 to 7VA-MVSNet trained on 3 views · DTU evaluationoverall error (mm): 0.371 -> 0.370No clear effect
train with 5 views instead of 3VA-MVSNet (test N=7) · DTU evaluationoverall error (mm): 0.370 -> 0.369No clear effect
use one pyramid level (K=1) with MMP (ablation)VA-MVSNet · DTU evaluationoverall error (mm): 0.369 -> 0.361Improved
increase pyramid levels from K=1 to K=3 (ablation)PVA-MVSNet · DTU evaluationcompleteness error (mm): 0.350 -> 0.336Mixed
add multi-metric pyramid aggregation and view aggregation vs MVSNetPVA-MVSNet · Tanks and Temples (no fine-tuning)mean f-score: 43.48 -> 54.46Improved

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