AI Paper Atlas

Research map / Architectures and efficiency / CNN design

A Scalable Distributed Framework for Multimodal GigaVoxel Image Registration

Rohit Jena, Vedant Zope, Pratik Chaudhari, James Gee

ICLR 2026 · Architectures and efficiency › CNN design · approach: Dense matching and estimation CNNs · 0 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 fused kernels to TransMorph LNCC trainingTransMorph-large · OASIS (LNCC)training time (h): 171.20 -> 27.84Improved
add fused kernels to TransMorph LNCC trainingTransMorph-large · OASIS (LNCC)GPU memory (GB): 20.01 -> 16.95Improved
add fused kernels to TransMorph LNCC trainingTransMorph-large · OASIS (LNCC)validation DSC: 86.74 -> 87.23Improved
add fused kernels to TransMorph MI trainingTransMorph-large · OASIS (MI)GPU memory (GB): 22.34 -> 16.80Improved
add fused kernels to TransMorph MI trainingTransMorph-large · OASIS (MI)training time (h): 26.09 -> 24.94Improved
add fused LNCC kernel to FireANTsFireANTs · FireANTs LNCCruntime (s): 1.44 -> 0.50Improved
add fused LNCC kernel to FireANTsFireANTs · FireANTs LNCCmemory (MB): 1044.5 -> 577.5Improved
add fused LNCC kernel to FireANTsFireANTs · FireANTs LNCCDice score: 78.81 -> 78.67No clear effect
use fused MI kernel instead of PyTorch MIFireANTs · FireANTs MImemory (MB): 12206.3 -> 577.5Improved
use fused MI kernel instead of PyTorch MIFireANTs · FireANTs MIruntime (s): 7.51 -> 2.90Improved
use torch.compile instead of fused LNCCFireANTs · FireANTs LNCCDice score: 78.67 -> 69.35Hurt
add ring sampler to FFDP (ablation)FFDP · weak scaling, 700x700x700H syntheticpeak HBM memoryImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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