AI Paper Atlas

Research map / 3D vision / Depth and stereo

FLaME: Fast Lightweight Mesh Estimation Using Variational Smoothing on Delaunay Graphs

W. Nicholas Greene, Nicholas Roy

ICCV 2017 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 25 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 FLaME (L=5) instead of MLMFLaME · EuRoC benchmarkrelative inverse depth error (%): 17 -> 10Improved
use FLaME (L=4) instead of MLMFLaME · TUM benchmarkrelative inverse depth error (%): 12 -> 6.8Improved
use FLaME (L=4) instead of MLMFLaME · TUM benchmarkdensity of accurate depth (%): 32 -> 54Improved
use FLaME (L=5) instead of LSD-SLAMFLaME · EuRoC benchmarkprocessing time per frame (ms): 16 -> 4.3Improved
increase detail parameter L from 3 to 5 (ablation)FLaME · EuRoC benchmarkrelative inverse depth error (%): 12 -> 10Improved
increase detail parameter L from 3 to 5 (ablation)FLaME · EuRoC benchmarkdensity of accurate depth (%): 36 -> 33Hurt
increase detail parameter L from 3 to 5 (ablation)FLaME · TUM benchmarkprocessing time per frame (ms): 16 -> 4.2Improved
add 1 cm translation noise to ground-truth poses (ablation)FLaME · TUM fr3 stfdensity of accurate depth (%): 71 -> 30Hurt

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