AI Paper Atlas

Research map / 3D vision / Depth and stereo

Taking the Scenic Route to 3D: Optimising Reconstruction From Moving Cameras

Oscar Mendez, Simon Hadfield, Nicolas Pugeault, Richard Bowden

ICCV 2017 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 23 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
use scenic information-gain path planning instead of shortest-path RRT*Scenic Pathplanner · Offline UAV room dataset, coveragecoverage: explores faster than both competing pathplanners while achieving a higher final coverageImproved
use scenic planner instead of PRMScenic Pathplanner · Offline UAV room dataset, average point erroraverage errorImproved
use scenic planner instead of RRT* in frames 30-50Scenic Pathplanner · Offline UAV room dataset, average point erroraverage error: worse than RRT* between frames 30 - 50Hurt
use scenic planner instead of VisualSFM+CMVS batchScenic Pathplanner · Offline UAV room dataset, outlier ratiooutlier ratio: maintaining around 10% outliersImproved
increase gamma from 0 toward 1 (unobserved-ray cost) (ablation)Scenic Pathplanner · Online ground robot room, coveragecoverage vs pairs: gamma = 0 explores rapidly; gamma toward 1 reduces reward of explorationMixed

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