AI Paper Atlas

Research map / 3D vision / Depth and stereo

Incremental Non-Rigid Structure-from-Motion with Unknown Focal Length

Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool

ECCV 2018 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 9 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 estimated focal length f_est instead of ground-truth focal lengthtemplate-based NRSfM · KINECT Paperreconstruction error (mm): 3.00 -> 2.83Improved
use estimated focal length f_est instead of ground-truth focal lengthtemplate-based NRSfM · Hulkreconstruction error (mm): 5.73 -> 5.53Improved
use estimated focal length f_est instead of ground-truth focal lengthtemplate-based NRSfM · Flagreconstruction error (mm): 4.74 -> 4.54Improved
use estimated focal length f_est instead of ground-truth focal lengthtemplate-less NRSfM · Newspaperreconstruction error (mm): 7.79 -> 9.27Hurt
add gradient-based refinement to the template-based focal estimate (ablation)template-based calibration · Hulkfocal length error (%): 13.61 -> 8.85Improved
add gradient-based refinement to the template-based focal estimate (ablation)template-based calibration · KINECT Paperfocal length error (%): 11.74 -> 14.45Hurt
add gradient-based refinement to the template-based focal estimate (ablation)template-based calibration · Flagreconstruction error (mm): 4.54 -> 4.34Improved
add gradient-based refinement from noisy initial K (+-20% noise)calibration refinement · Hulk (simulated initial K)focal length error (%): -2.36Improved
add gradient-based refinement from noisy initial K (+-20% noise)calibration refinement · Flag (simulated initial K)reconstruction error (mm): +0.08No clear effect
use incremental reconstruction (incr-tlmdh) instead of batch tlmdhtemplate-less NRSfM · KPaperrun time: 605.06s -> 176.16sImproved
use incremental reconstruction (incr-tlmdh) instead of batch tlmdhtemplate-less NRSfM · KPapermean 3D error (mm): 5.41 -> 4.64Improved
use incremental reconstruction (incr-tlmdh) instead of batch tlmdhtemplate-less NRSfM · Hulkmean 3D error (mm): 2.76 -> 2.99Hurt

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