AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Iterative Continuous Convolution for 3D Template Matching and Global Localization

Vitor Guizilini, Fabio Ramos

AAAI 2018 · Architectures and efficiency › CNN design · approach: Dense matching and estimation CNNs · 3 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
Replace GEN-ICP with CC-HM3D template matching · Corridorcomputation time (s): 55.9 -> 2.9Improved
Replace GEN-ICP with CC-HM3D template matching · Corridorlinear error (cm): 11.9 -> 14.5Hurt
Replace GEN-ICP with CC-HM3D template matching · Outdoorlinear error (cm): 15.5 -> 17.1Hurt
Add iterative convolution (ICC-HM) on top of CC-HM (ablation)CC-HM · Corridorlinear error (cm): 14.5 -> 9.8Improved
Add iterative convolution (ICC-HM) on top of CC-HM (ablation)CC-HM · Outdoorlinear error (cm): 17.1 -> 10.9Improved
Add iterative convolution (ICC-HM) on top of CC-HM (ablation)CC-HM · Corridorcomputation time (s): 2.9 -> 4.1Hurt
Add iterative convolution (ICC-HM) on top of CC-HM (ablation)CC-HM · Corridorangular error (deg): 4.4 -> 3.1Improved
Use ICC-HM output to initialize GEN-ICP (ICC-ICP) (ablation)ICC-HM · Corridorlinear error (cm): 9.8 -> 9.5Improved
Use ICC-HM output to initialize GEN-ICP (ICC-ICP) (ablation)ICC-HM · Outdoorcomputation time (s): 5.7 -> 9.3Hurt
Continuous convolution instead of Fourier convolution at 0.02 mconvolution · Convolution timinginference time (us/pt): 5.1 -> 1.0Improved
Continuous convolution instead of sliding convolution at 0.02 mconvolution · Convolution timinggrid generation time (ms/m3): 167.9 -> 2.5Improved
Use continuous convolution at very small mask sizesconvolution · speed vs mask sizespeedHurt

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