AI Paper Atlas

Research map / 3D vision / Depth and stereo

A Benchmark and Evaluation of Non-Rigid Structure from Motion

Sebastian Hoppe Nesgaard Jensen, Mads Emil Brix Doest, Henrik Aanæs, Alessio Del Bue

IJCV 2020 · 3D vision › Depth and stereo · approach: Camera model and calibration for SfM · 44 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
switch from orthographic to full perspective camera model18 NRSfM methods · NRSfM benchmarkmean reconstruction error (mm): 50.45 -> 57.66Hurt
add occlusion-based missing dataMetricProj · NRSfM benchmarkmean reconstruction error (mm): increase of 5.85mmHurt
add occlusion-based missing dataKSTA · NRSfM benchmarkmean reconstruction error (mm): 9.65mmHurt
add occlusion-based missing dataCSF2 · NRSfM benchmarkmean reconstruction error (mm): 18.15mmHurt
add occlusion-based missing dataCSF · NRSfM benchmarkmean reconstruction error (mm): 13.49mmHurt
add occlusion-based missing dataScalableSurface (DCT basis) · NRSfM benchmarkmean reconstruction error (mm): 16.52mmHurt
add occlusion-based missing dataBALM · NRSfM benchmarkmean reconstruction error (mm): decreases by 3.33mmImproved
add occlusion-based missing data to in-plane deformations (Tearing, Stretching, Articulated)NRSfM methods · NRSfM benchmarkmean reconstruction error (mm): 3.96mm, 4.65mm and 8.38mmHurt
add occlusion-based missing data to volumetric deformations (Deflation, Bending)NRSfM methods · NRSfM benchmarkmean reconstruction error (mm): 12.27mm and 13.47mmHurt
use Circle camera path instead of ZigzagNRSfM methods · NRSfM benchmarkmean reconstruction error (mm): 47.29 -> 61.18Hurt
use Tricky versus Circle camera path (designed to be harder)NRSfM methods · NRSfM benchmarkmean reconstruction error (mm): differ by 3.08mmNo clear effect
physical deformation priors (MDH, SoftInext) instead of statistical modelsMDH / SoftInext · NRSfM benchmarkmean reconstruction error (mm): 70.34 and 61.94 vs MultiBody 29.36Hurt

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