AI Paper Atlas

Research map / 3D vision / Depth and stereo

Pixel-Perfect Structure-From-Motion With Featuremetric Refinement

Philipp Lindenberger, Paul-Edouard Sarlin, Viktor Larsson, Marc Pollefeys

ICCV 2021 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 205 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 featuremetric refinement to SIFTSIFT · ETH3D triangulation (indoor)accuracy @1cm (%): 75.62 -> 82.82Improved
add featuremetric refinement to SuperPointSuperPoint · ETH3D triangulation (indoor)accuracy @1cm (%): 75.76 -> 89.33Improved
add featuremetric refinement to D2-NetD2-Net · ETH3D triangulation (indoor)accuracy @1cm (%): 47.18 -> 82.49Improved
replace Patch Flow with featuremetric keypoint refinementSIFT · ETH3D camera pose estimationAUC @1mm (%): 14.62 -> 25.38Improved
add featuremetric refinement to SuperPoint localizationSuperPoint · ETH3D camera pose estimationAUC @1mm (%): 15.38 -> 40.00Improved
add featuremetric refinement to SuperPoint+SuperGlueSuperPoint+SuperGlue · IMC 2020 multiviewAUC @5 deg@N=5 (%): 63.02 -> 68.87Improved
add featuremetric refinement to D2-NetD2-Net · IMC 2020 stereoAUC @5 deg (%): 16.83 -> 25.89Improved
add featuremetric bundle adjustment after keypoint adjustment (ablation)SuperPoint F-KA · ETH3D Facadetriangulation accuracy @1cm (%): 36.85 -> 46.46Improved
add featuremetric keypoint adjustment before bundle adjustment (ablation)SuperPoint F-BA · ETH3D Facadetriangulation accuracy @1cm (%): 43.65 -> 46.46Improved
use S2DNet features instead of photometric NCC (ablation)SuperPoint refinement · ETH3D Facadetriangulation accuracy @1cm (%): 28.43 -> 46.46Improved
let BA reference features drift (ablation)SuperPoint full · ETH3D Facadelocalization AUC @1cm (%): 71.97 -> 64.51Mixed
add query keypoint adjustment (qKA) before pose estimation (ablation)SuperPoint KA+BA · ETH3D camera poseAUC @1mm (%): 16.92 -> 38.46Improved

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