AI Paper Atlas

Research map / 3D vision / Depth and stereo

Multi-View Stereo by Temporal Nonparametric Fusion

Yuxin Hou, Juho Kannala, Arno Solin

ICCV 2019 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 90 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 GP prior on latent space with Matern pose kernel (ablation)MVDepthNet-style encoder-decoder · Kernel ablationL1-rel: 0.1538 -> 0.1298Improved
add GP prior on latent space with Matern pose kernel (ablation)MVDepthNet-style encoder-decoder · Kernel ablationL1: 0.3265 -> 0.2769Improved
use pose-distance Matern kernel instead of exponential kernel (ablation)GP-MVS · Kernel ablationL1-rel: 0.1376 -> 0.1298Improved
use pose-distance Matern kernel instead of temporal-difference kernel (ablation)GP-MVS · Kernel ablationL1-rel: 0.1450 -> 0.1298Improved
use temporal-difference kernel instead of no GP (ablation)GP-MVS · Kernel ablationL1-rel: 0.1538 -> 0.1450Improved
add GP prior with small translation threshold (ablation)GP-MVS · SUN3D + 7scenes (t_min=0.1 m)L1-rel: 0.1474 -> 0.1238Improved
add GP prior with smaller translation threshold (ablation)GP-MVS · SUN3D + 7scenes (t_min=0.05 m)L1-rel: 0.1535 -> 0.1262Improved
lower translation threshold from 0.1 m to 0.05 m, no GP (ablation)GP-MVS w/o GP · SUN3D + 7scenesL1-rel: 0.1474 -> 0.1535Hurt
lower translation threshold from 0.1 m to 0.05 m, with GP (ablation)GP-MVS · SUN3D + 7scenesL1-rel: 0.1238 -> 0.1262No clear effect
use 5 input frames instead of 2 (ablation)GP-MVS · 7scenes redkitchen-02L1-rel: 0.1615 -> 0.1429Improved
add GP prior to MVDepthNet with 2 frames (ablation)MVDepthNet · 7scenes redkitchen-02 (2 frames)L1-rel: 0.2009 -> 0.1615Improved
add GP prior (online inference) over MVDepthNet at test timeMVDepthNet · Inference time (desktop)seconds per frame: 0.066 -> 0.076Hurt

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