AI Paper Atlas

Research map / 3D vision / Face and shape

NAB: Neural Adaptive Binning for Sparse-View CT reconstruction

Wangduo Xie, Matthew B. Blaschko

ICLR 2026 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 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
replace random Fourier encoding with NABINR_f · CaCO3 (16-view)PSNR (dB): 29.01 -> 43.61Improved
replace random Fourier encoding with NABINR_f · CaCO3 (12-view)PSNR (dB): 25.08 -> 34.72Improved
replace random Fourier encoding with NABINR_f · Workpieces (12-view)PSNR (dB): 27.37 -> 32.76Improved
replace random Fourier encoding with NABINR_f · Workpieces (14-view)PSNR (dB): 34.03 -> 35.23Improved
use NAB with 4-layer FCN instead of 7-layer wider INR_l2INR_l2 · CaCO3 (16-view)PSNR (dB): 38.89 -> 43.61Improved
train 29,990 epochs instead of 19,990NAB · CaCO3 (14-view)PSNR (dB): 36.09 -> 40.07Improved
add trainable bin center location (ablation)NAB · CaCO3 (16-view)PSNR (dB): 29.82 -> 43.61Improved
add trainable bin side length (ablation)NAB · CaCO3 (16-view)PSNR (dB): 30.82 -> 43.61Improved
add bin rotation (ablation)NAB · CaCO3 (16-view)PSNR (dB): 37.50 -> 43.61Improved
add trainable steepness (ablation)NAB · CaCO3 (16-view)PSNR (dB): 42.91 -> 43.61Improved
add trainable bin height (ablation)NAB · CaCO3 (16-view)PSNR (dB): 43.37 -> 43.61No clear effect
use NAB instead of Instant-NGPInstant-NGP · CaCO3 (12-view)SSIM: 0.911 -> 0.888Hurt

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