AI Paper Atlas

Research map / 3D vision / Depth and stereo

IS-MVSNet: Importance Sampling-Based MVSNet

Likang Wang, Yue Gong, Xinjun Ma, Qirui Wang, Kaixuan Zhou, Lei Chen

ECCV 2022 · 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 importance sampling (geometric interval) instead of uniform sampling (ablation)IS-MVSNet · ETH3D training set (2cm), stage 3F-score: 0.44 -> 0.58Improved
add importance sampling instead of uniform sampling (ablation)IS-MVSNet · ETH3D training set (2cm), stage 2F-score: 0.32 -> 0.41Improved
add importance sampling instead of uniform sampling (ablation)IS-MVSNet · ETH3D training set (2cm), stage 1F-score: 0.14 -> 0.14No clear effect
convert i.i.d. uniform sampling to identical interval sampling (ablation)uniform sampling · ETH3D high-res training setF-score: 6.4% F-score improvementImproved
sample depths from zero-mean Gaussian (i.i.d.) rather than uniform (ablation)IS-MVSNet · ETH3DF-scoreImproved
increase k above 1 (denser sampling near previous prediction) (ablation)IS-MVSNet · ETH3D and DTUF-score / overall distanceMixed
select k with unsupervised ternary search on photometric variance (ablation)IS-MVSNet · ETH3DF-scoreImproved
use two reference views per scene for k estimation (ablation)IS-MVSNet · ETH3Dvariance estimateNo clear effect
use importance sampling in place of uniform sampling in Vis-MVSNetIS-MVSNet · DTU testing setoverall distance (mm): 0.365 -> 0.355Improved
use importance sampling in place of uniform sampling in Vis-MVSNetIS-MVSNet · Tanks & Temples intermediateF-score mean (%): 60.03 -> 62.82Improved

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