AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Vis2Mesh: Efficient Mesh Reconstruction From Unstructured Point Clouds of Large Scenes With Learned Virtual View Visibility

Shuang Song, Zhaopeng Cui, Rongjun Qin

ICCV 2021 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 19 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 depth completion module (VDVNet cascade) (ablation)visibility network · BlendedMVS pixel-wise visibilityF1 (%): 93.01 -> 93.63Improved
add depth completion when partial convolution is absent (ablation)visibility network · BlendedMVS pixel-wise visibilityF1 (%): 87.71 -> 92.21Improved
add partial convolution layers (ablation)visibility network · BlendedMVS pixel-wise visibilityF1 (%): 92.21 -> 93.63Improved
add partial convolution to UNet (ablation)UNet · BlendedMVS pixel-wise visibilityF1 (%): 88.68 -> 89.32Improved
add partial convolution layers in full pipeline (ablation)visibility network · BlendedMVS pixel-wise visibilityAUC (%): 93.14 -> 94.17Improved
use learned VDVNet instead of geometric HPRvisibility estimation · BlendedMVS pixel-wise visibilityAUC (%): 82.22 -> 94.17Improved
add adaptive visibility weighting (gamma_av=1) on outdoor scenes (ablation)Vis2Mesh · Outdoor 500K (average)F-score: 0.9634 -> 0.9654Improved
add adaptive visibility weighting on outdoor scenes (ablation)Vis2Mesh · Outdoor 500K (average)Chamfer distance: 0.2890 -> 0.2770Improved
add adaptive visibility weighting on object scenes (ablation)Vis2Mesh · Object 25K (average)Chamfer distance: 0.1959 -> 0.1846Improved
add adaptive visibility weighting on BlendedMVS scenes (ablation)Vis2Mesh · BlendedMVS MVS (average)F-score: 0.7215 -> 0.7321Improved
use virtual view visibility instead of real per-point LiDAR visibilityVis2Mesh · Mai City Datasetvisual qualityImproved
increase number of virtual views (ablation)Vis2Mesh · qualitative scenevisual detailImproved

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