Research map / Architectures and efficiency / CNN design
A Scalable Distributed Framework for Multimodal GigaVoxel Image Registration
Rohit Jena, Vedant Zope, Pratik Chaudhari, James Gee
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add fused kernels to TransMorph LNCC training | TransMorph-large · OASIS (LNCC) | training time (h): 171.20 -> 27.84 | Improved |
| add fused kernels to TransMorph LNCC training | TransMorph-large · OASIS (LNCC) | GPU memory (GB): 20.01 -> 16.95 | Improved |
| add fused kernels to TransMorph LNCC training | TransMorph-large · OASIS (LNCC) | validation DSC: 86.74 -> 87.23 | Improved |
| add fused kernels to TransMorph MI training | TransMorph-large · OASIS (MI) | GPU memory (GB): 22.34 -> 16.80 | Improved |
| add fused kernels to TransMorph MI training | TransMorph-large · OASIS (MI) | training time (h): 26.09 -> 24.94 | Improved |
| add fused LNCC kernel to FireANTs | FireANTs · FireANTs LNCC | runtime (s): 1.44 -> 0.50 | Improved |
| add fused LNCC kernel to FireANTs | FireANTs · FireANTs LNCC | memory (MB): 1044.5 -> 577.5 | Improved |
| add fused LNCC kernel to FireANTs | FireANTs · FireANTs LNCC | Dice score: 78.81 -> 78.67 | No clear effect |
| use fused MI kernel instead of PyTorch MI | FireANTs · FireANTs MI | memory (MB): 12206.3 -> 577.5 | Improved |
| use fused MI kernel instead of PyTorch MI | FireANTs · FireANTs MI | runtime (s): 7.51 -> 2.90 | Improved |
| use torch.compile instead of fused LNCC | FireANTs · FireANTs LNCC | Dice score: 78.67 -> 69.35 | Hurt |
| add ring sampler to FFDP (ablation) | FFDP · weak scaling, 700x700x700H synthetic | peak HBM memory | Improved |
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.
- PyTorch — PyTorch: An Imperative Style, High-Performance Deep Learning Library (NeurIPS 2019) · better on 3 of 3 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
- Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration (CVPR 2024 · similarity 0.85)
- A Plug-and-Play Image Registration Network (ICLR 2024 · similarity 0.83)
- A Steerable Deep Network for Model-Free Diffusion MRI Registration (NeurIPS 2026 · similarity 0.83)
- PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference (NeurIPS 2025 · similarity 0.83)
- Deep Learning in Medical Image Registration: Magic or Mirage? (NeurIPS 2024 · similarity 0.83)
- Sparse-to-dense Multimodal Image Registration via Multi-Task Learning (ICML 2024 · similarity 0.82)
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.
